Team
Julia Neidhardt
Researcher & Lab Director
Julia Neidhardt is a researcher at the Research Unit E-Commerce at TU Wien informatics with a background in mathematics and computer science. Previously she was a guest researcher at the Austrian Academy of Sciences as well as visiting scholar at Northwestern University, USA, and at the University of Geneva, Switzerland. Her research focuses on user modeling and recommender systems in tourism and in the news domain, developing approaches to capture online opinion-forming and online behavior, and digital humanities. Her research is published in highly renowned conference proceedings and journals including Nature Human Behaviour. She regularly is invited to give talks on topics related to her research, among others at the Oxford Women in Computer Science – Distinguished Speaker Series at the University of Oxford. Julia Neidhardt is a senior program committee member of the ACM Conference on Recommender Systems (RecSys) and is an associate editor of the Journal of Information Technology &Tourism as well as a distinguished reviewer of the newly established journal ACM Transactions on Recommender Systems (TORS). She was research track co-chair of ENTER 2020 and ENTER 2019 and a co-organizer of a number of workshops and conferences. Julia Neidhardt is part of the Digital Humanism Initiative at TU Wien and board member of Center for Artificial Intelligence and Machine Learning (CAIML). She will lead the CD Lab for Recommender Systems, applying her expertise in these various research areas focusing on recommender systems.
Supervisions
- Analysis of the Performance of a Conversational Recommender System in Online Fashion E-Commerce (in progress). Bachelor’s Thesis.
- Analysing Dynamics Over Time of Bias in Recommender Systems (in progress). Boris Staykov. Master’s Thesis.
- Automated Fine-Grained Location Tagging in Online News (in progress). Master’s Thesis.
- Data Transformation Tool to Explore News Recommenders (in progress). Manuel Feuerstein. Bachelor’s Thesis.
- Advancing Session-Based Recommendations: Integrating Modern LLMs and Micro-Behaviors (in progress). Florian Dedov. Master’s Thesis.
- Intent Discovery and Product Search for Price Comparison Sites (in progress). Dante Godolja. Master’s Thesis.
- POI Recommender Systems for Customized Walking Tours Using Context and Category (in progress). Joanna Zamiechowska. Master’s Thesis.
- Enhancing Video Segment Discovery in Educational Content: A Conversational Approach with Retrieval-Augmented Generation (in progress). Dragana Naceva. Master’s Thesis.
- The Role of Clarifying Questions in Conversational Recommender Systems: Balancing Explicitness (in progress). Anna Baghumyan. Master’s Thesis.
- Evaluating Agentic Retrieval Augmented Generation in Open Tender Evaluations (in progress). Franz Ottitsch. Master’s Thesis.
- Examining Tech Bias: Analyzing Career Recommendations in LLMs through Demographic Persona-Based Prompting (completed). 2026. Bachelor’s Thesis.
- The Impact of Using Large Language Models on the Performance of Recommender Systems (completed). Michael Schmiedmayer. 2026. Master’s Thesis.
- Bias in Medical Recommendations: Prompting vs. Fine-tuning of Large Language Models (completed). Daha Pavlovic. 2026. Master’s Thesis.
- Data-Centric AI for Conceptual Modeling: Cleansed Data and GNN-LLM based Recommender for UML Class Diagrams (completed). Andjela Djelic. 2026. Master’s Thesis.
- Temporal Analysis of Session Clusters in Clickstream Data from a Price Comparison Platform (completed). Luca Turin. 2026. Bachelor’s Thesis.
- Exploration of Intermediate Fusion Strategies: Between Graph and Text Modalities in Session-Based Recommender Systems (completed). Roman Grebnev. 2025. Master’s Thesis.
- Choice-Based Preference Elicitation to Reduce the Cold Start Problem of a Leisure Activities Recommender in a Mobile App (completed). Andreas Fink. 2025. Master’s Thesis.
- Comparative Analysis of Fashion Captioning and Multimodal Fashion Recommendation (completed). Maria De Los Angeles Gwendolyn Aglae Rippberger Fonseca. 2025. Master’s Thesis.
- Context over Categories – Implementing the Theory of Constructed Emotion (completed). Nils Klüwer. 2025. Master’s Thesis.
- Evaluating the Fairness of News Recommender Algorithms Within Detected User Communities (completed). Bernhard Steindl. 2024. Master’s Thesis.
- Exploration of Content-Based Cross-Domain Podcast Recommender Systems (completed). Matthias Hofmaier. 2024. Master’s Thesis.
- Measuring Controversy in Online Discussions (completed). Ivan Andreev. 2024. Bachelor’s Thesis.
- Classification of users in an online news forum – a data analysis of user types and user interaction in the online forum of an Austrian newspaper (completed). Felix Scholz. 2023. Master’s Thesis.
- Network Analysis on the Austrian Media Corpus: Examining measures of co-occurrence between entities in Austrian media (completed). Gabriel Grill. 2023. Master’s Thesis.
- Wie wirken sich technologische Filterblasen, als Folge der algorithmisch personalisierten Aufbereitung von Inhalten sozialer Netzwerke, auf die politische Meinungspolarisierung der Nutzer:innen aus? (completed). Nadine Chincea. 2023. Bachelor’s Thesis.
- How Can Digital Nudges Guide Users Towards More Diverse News Consumption? (completed). Laura Valentina Modre. 2023. Bachelor’s Thesis.
- Diversity in News Recommendations- Towards a Broader Perspective on Diversity-Aware-Recommender-Systems and Their Influence on Users (completed). Linda Basso. 2023. Bachelor’s Thesis.
- Improving Trust in Recommender Systems through Context Clues (completed). Tobias Sippl. 2023. Bachelor’s Thesis.
- Exploring the Sentiment Patterns of Clustered COVID-19 News Articles on Mask Requirements: A Comparison with User Comments (completed). Lukas Burtscher. 2023. Bachelor’s Thesis.
- Content-Based Restaurant Recommendation Systems Using Textual and Visual Data (completed). Dante Godolja. 2023. Bachelor’s Thesis.
- Exploring Group Fairness in News Media Recommendations: Algorithms, Metrics, and Grouping (completed). Blake Huebner. 2023. Master’s Thesis.
- COVID-19 and Populism in Austrian News User Comments – A Machine Learning Approach (completed). Ahmadou Wagne. 2023. Master’s Thesis.
- K-Means Clustering of Fashion Behavior: A Language-Focused Approach (completed). Florian Dedov. 2022. Bachelor’s Thesis.
- Merging the Gap Between Automated and Human Centered Usability Testing (completed). Can Özgür Yilmaz. 2022. Master’s Thesis.
- Exhibit Rating Prediction and Visitor Path Prediction in a Museum Setting (completed). Marek Furka. 2022. Master’s Thesis.
- Dynamic Sentiment Analysis for Measuring Media Bias (completed). Thomas E. Kolb. 2022. Master’s Thesis.
Publications
2019
Sertkan, Mete; Neidhardt, Julia; Werthner, Hannes
Von Reisezielmerkmalen zur Reisezielpersönlichkeit Journal Article
In: Tourismuswissen – quarterly, vol. APRIL, pp. 91–98, 2019.
@article{ 20.500.12708_143937,
title = {Von Reisezielmerkmalen zur Reisezielpersönlichkeit},
author = {Mete Sertkan and Julia Neidhardt and Hannes Werthner},
year = {2019},
date = {2019-01-01},
journal = {Tourismuswissen - quarterly},
volume = {APRIL},
pages = {91–98},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2018
Neidhardt, Julia; Werthner, Hannes
IT and tourism: still a hot topic, but do not forget IT Journal Article
In: Information Technology and Tourism, 2018, ISSN: 1098-3058.
@article{ 20.500.12708_255,
title = {IT and tourism: still a hot topic, but do not forget IT},
author = {Julia Neidhardt and Hannes Werthner},
doi = {10.1007/s40558-018-0115-x},
issn = {1098-3058},
year = {2018},
date = {2018-01-01},
journal = {Information Technology and Tourism},
publisher = {Springer},
abstract = {More and more aspects of our life “move” to the Web. The Web and the Internet, as the underlying information infrastructure and “machine”, can be considered as a mirror of the “real” physical world. However, the Web is not only reflecting this world, it is obviously also transforming it, where it is increasingly hard to distinguish between the physical and the virtual. It acts both as an enabler and driver of new, technical, economic and societal developments. With recent achievements in areas such as machine learning, Internet of Things or artificial intelligence (or rather intelligent assistance—a probably more appropriate term), we see the power of computer science. In this short comment, we argue that IT and tourism is still a hot topic, also or especially from a scientific point of view. However, from this latter point of view this might change, and we claim that, in order to prevent the field from becoming insignificant, more emphasis must be put on technical and formal aspects of science. We do not know the future, we are not “futurologists” (In a marketing note of an innovation and technology conference, the organizers even wanted to provide a look beyond the future—we have no idea how this nonsense could be done!), but we take the freedom to highlight some issues, which we consider to be important—in particular since one of the authors has a background of driving the field for nearly 30 years.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
More and more aspects of our life “move” to the Web. The Web and the Internet, as the underlying information infrastructure and “machine”, can be considered as a mirror of the “real” physical world. However, the Web is not only reflecting this world, it is obviously also transforming it, where it is increasingly hard to distinguish between the physical and the virtual. It acts both as an enabler and driver of new, technical, economic and societal developments. With recent achievements in areas such as machine learning, Internet of Things or artificial intelligence (or rather intelligent assistance—a probably more appropriate term), we see the power of computer science. In this short comment, we argue that IT and tourism is still a hot topic, also or especially from a scientific point of view. However, from this latter point of view this might change, and we claim that, in order to prevent the field from becoming insignificant, more emphasis must be put on technical and formal aspects of science. We do not know the future, we are not “futurologists” (In a marketing note of an innovation and technology conference, the organizers even wanted to provide a look beyond the future—we have no idea how this nonsense could be done!), but we take the freedom to highlight some issues, which we consider to be important—in particular since one of the authors has a background of driving the field for nearly 30 years.
Delic, Amra; Neidhardt, Julia; Nguyen, Thuy Ngoc; Ricci, Francesco
An observational user study for group recommender systems in the tourism domain Journal Article
In: Information Technology and Tourism, vol. 19, iss. 1-4, pp. 87–116, 2018, ISSN: 1098-3058.
@article{ 20.500.12708_83,
title = {An observational user study for group recommender systems in the tourism domain},
author = {Amra Delic and Julia Neidhardt and Thuy Ngoc Nguyen and Francesco Ricci},
doi = {10.1007/s40558-018-0106-y},
issn = {1098-3058},
year = {2018},
date = {2018-01-01},
journal = {Information Technology and Tourism},
volume = {19},
issue = {1-4},
pages = {87–116},
publisher = {SPRINGER HEIDELBERG},
abstract = {In this article we argue and give evidence that the research on group recommender systems must look more carefully at the dynamics of group decision-making in order to produce technologies that will be truly beneficial for groups. We illustrate the adopted research method and the results of a user study aimed at observing and measuring the evolution of user preferences and interaction in a tourism decision-making task: finding a destination to visit together as a group. We discuss the benefits and caveats of such an observational study method and we present the implications that the derived data and findings have on the design of interactive group recommender systems.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this article we argue and give evidence that the research on group recommender systems must look more carefully at the dynamics of group decision-making in order to produce technologies that will be truly beneficial for groups. We illustrate the adopted research method and the results of a user study aimed at observing and measuring the evolution of user preferences and interaction in a tourism decision-making task: finding a destination to visit together as a group. We discuss the benefits and caveats of such an observational study method and we present the implications that the derived data and findings have on the design of interactive group recommender systems.
Neidhardt, Julia; Wörndl, Wolfgang; Kuflik, Tsvi; Zanker, Markus
ACM recsys workshop on recommenders in tourism (rectour 2018) Proceedings Article
In: Proceedings of the 12th ACM Conference on Recommender Systems, ACM Digital Library, New York, 2018.
@inproceedings{ 20.500.12708_57718,
title = {ACM recsys workshop on recommenders in tourism (rectour 2018)},
author = {Julia Neidhardt and Wolfgang Wörndl and Tsvi Kuflik and Markus Zanker},
doi = {10.1145/3240323.3240341},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 12th ACM Conference on Recommender Systems},
publisher = {ACM Digital Library},
address = {New York},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Neidhardt, Julia
Social Influence and Opinion Forming in Online Social Networks. Miscellaneous
2018.
@misc{ 20.500.12708_86851,
title = {Social Influence and Opinion Forming in Online Social Networks.},
author = {Julia Neidhardt},
year = {2018},
date = {2018-01-01},
abstract = {Web-based phenomena such as fake news, hate speech or echo chambers have been gaining increasing attention in the public discourse. However, the extent and actual impact of these phenomena are still unknown. In order to address these issues in more depth, it is important to understand how opinions emerge, change and get exchanged. In our work, we therefore intend to develop data-driven approaches to examine social influence mechanisms and opinion forming at a large scale.
We aim, in particular, to introduce a complex user model, which characterizes each person with respect to three levels: 1) the individual level capturing the characteristics of a user; 2) the network level capturing the social relationships of a user; and 3) the group level describing sets of similar users with certain dominant opinions and high-level ideologies. We introduce the concepts based on a rich and unique dataset of an online news forum that contains the complete posting history of all users, their detailed behaviors and interactions as well as all news articles and the respective meta data for almost two decades.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Web-based phenomena such as fake news, hate speech or echo chambers have been gaining increasing attention in the public discourse. However, the extent and actual impact of these phenomena are still unknown. In order to address these issues in more depth, it is important to understand how opinions emerge, change and get exchanged. In our work, we therefore intend to develop data-driven approaches to examine social influence mechanisms and opinion forming at a large scale.
We aim, in particular, to introduce a complex user model, which characterizes each person with respect to three levels: 1) the individual level capturing the characteristics of a user; 2) the network level capturing the social relationships of a user; and 3) the group level describing sets of similar users with certain dominant opinions and high-level ideologies. We introduce the concepts based on a rich and unique dataset of an online news forum that contains the complete posting history of all users, their detailed behaviors and interactions as well as all news articles and the respective meta data for almost two decades.
We aim, in particular, to introduce a complex user model, which characterizes each person with respect to three levels: 1) the individual level capturing the characteristics of a user; 2) the network level capturing the social relationships of a user; and 3) the group level describing sets of similar users with certain dominant opinions and high-level ideologies. We introduce the concepts based on a rich and unique dataset of an online news forum that contains the complete posting history of all users, their detailed behaviors and interactions as well as all news articles and the respective meta data for almost two decades.
Sertkan, Mete; Neidhardt, Julia; Werthner, Hannes
Mapping of Tourism Destinations to Travel Behavioural Patterns Proceedings Article
In: Information and Communication Technologies in Tourism 2018, pp. 422–434, Springer, Cham, 2018, ISBN: 9783319729237.
@inproceedings{ 20.500.12708_57174,
title = {Mapping of Tourism Destinations to Travel Behavioural Patterns},
author = {Mete Sertkan and Julia Neidhardt and Hannes Werthner},
doi = {10.1007/978-3-319-72923-7_32},
isbn = {9783319729237},
year = {2018},
date = {2018-01-01},
booktitle = {Information and Communication Technologies in Tourism 2018},
pages = {422–434},
publisher = {Springer, Cham},
abstract = {Tourism is an information intensive domain, where recommender systems have become an essential tool to guide customers to the right products. However, they are facing major challenges, since tourism products are considered as complex and emotional. It has been shown that the seven-factor model is a legitimate way to counter some of these challenges. However, in order to recommend an item, it has also to be described in terms of this model. This work´s aim is to find a scalable way to map tourism destinations, defined by their attributes, to the seven-factor model. Through statistical analysis and learning methods it is shown that there is a significant relationship between particular destination features and the seven-factors and that destinations can be grouped in a meaningful way using their attributes.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Tourism is an information intensive domain, where recommender systems have become an essential tool to guide customers to the right products. However, they are facing major challenges, since tourism products are considered as complex and emotional. It has been shown that the seven-factor model is a legitimate way to counter some of these challenges. However, in order to recommend an item, it has also to be described in terms of this model. This work´s aim is to find a scalable way to map tourism destinations, defined by their attributes, to the seven-factor model. Through statistical analysis and learning methods it is shown that there is a significant relationship between particular destination features and the seven-factors and that destinations can be grouped in a meaningful way using their attributes.
Delic, Amra; Neidhardt, Julia; Werthner, Hannes
Group Decision Making and Group Recommendations in Tourism Domain Proceedings Article
In: CBI 2018 – Proceedings of the 20th IEEE International Conference on Business Informatics, IEEE, 2018.
@inproceedings{ 20.500.12708_57392,
title = {Group Decision Making and Group Recommendations in Tourism Domain},
author = {Amra Delic and Julia Neidhardt and Hannes Werthner},
year = {2018},
date = {2018-01-01},
booktitle = {CBI 2018 - Proceedings of the 20th IEEE International Conference on Business Informatics},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Delic, Amra; Masthoff, Judith; Neidhardt, Julia; Werthner, Hannes
How to Use Social Relationships in Group Recommenders Proceedings Article
In: Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization, ACM New York, 2018.
@inproceedings{ 20.500.12708_57391,
title = {How to Use Social Relationships in Group Recommenders},
author = {Amra Delic and Judith Masthoff and Julia Neidhardt and Hannes Werthner},
doi = {10.1145/3209219.3209226},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization},
publisher = {ACM New York},
abstract = {In this paper we present the results of a user study focusing on social relationships within small groups. The goal is to better understand how to incorporate the information about social relationships in group recommendation models. Our analysis, conducted on a data set of 150 participants in 41 groups deciding on a travel destination to visit together, brings out some intriguing outcomes. We demonstrate that social centrality is hardly an indicator of the social influence in the decision-making process of "equality matching" types of groups. However, socially central group members and socially close groups are significantly happier with group decisions than those who are loosely related. Moreover, in this paper we show that social relationships are indicators of other concepts relevant in group settings, therefore in group recommender systems as well.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we present the results of a user study focusing on social relationships within small groups. The goal is to better understand how to incorporate the information about social relationships in group recommendation models. Our analysis, conducted on a data set of 150 participants in 41 groups deciding on a travel destination to visit together, brings out some intriguing outcomes. We demonstrate that social centrality is hardly an indicator of the social influence in the decision-making process of "equality matching" types of groups. However, socially central group members and socially close groups are significantly happier with group decisions than those who are loosely related. Moreover, in this paper we show that social relationships are indicators of other concepts relevant in group settings, therefore in group recommender systems as well.
Mukherjee, Satyam; Huang, Yun; Neidhardt, Julia; Uzzi, Brian; Contractor, Noshir
Prior shared success predicts victory in team competitions Journal Article
In: Nature Human Behaviour, vol. 3, iss. 1, pp. 74–81, 2018, ISSN: 2397-3374.
@article{ 20.500.12708_145946,
title = {Prior shared success predicts victory in team competitions},
author = {Satyam Mukherjee and Yun Huang and Julia Neidhardt and Brian Uzzi and Noshir Contractor},
doi = {10.1038/s41562-018-0460-y},
issn = {2397-3374},
year = {2018},
date = {2018-01-01},
journal = {Nature Human Behaviour},
volume = {3},
issue = {1},
pages = {74–81},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Neidhardt, Julia; Kuflik, Tsvi; Wörndl, Wolfgang
Special Section on Recommender Systems in Tourism Journal Article
In: Information Technology and Tourism, vol. 19, iss. 1-4, pp. 83–85, 2018, ISSN: 1098-3058.
@article{ 20.500.12708_145947,
title = {Special Section on Recommender Systems in Tourism},
author = {Julia Neidhardt and Tsvi Kuflik and Wolfgang Wörndl},
doi = {10.1007/s40558-018-0111-1},
issn = {1098-3058},
year = {2018},
date = {2018-01-01},
journal = {Information Technology and Tourism},
volume = {19},
issue = {1-4},
pages = {83–85},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Glatzer, Lisa; Neidhardt, Julia; Werthner, Hannes
Automated Assignment of Hotel Descriptions to Travel Behavioural Patterns Proceedings Article
In: Information and Communication Technologies in Tourism 2018, pp. 409–421, Springer, 2018, ISBN: 9783319729237.
@inproceedings{ 20.500.12708_57173,
title = {Automated Assignment of Hotel Descriptions to Travel Behavioural Patterns},
author = {Lisa Glatzer and Julia Neidhardt and Hannes Werthner},
doi = {10.1007/978-3-319-72923-7_31},
isbn = {9783319729237},
year = {2018},
date = {2018-01-01},
booktitle = {Information and Communication Technologies in Tourism 2018},
pages = {409–421},
publisher = {Springer},
abstract = {The amount of people using online platforms to book a travel accommodation has grown tremendously. Hence, tour operators implement recommender systems to offer most suitable hotels to their customers. In this paper, a method of using hotel descriptions for recommendation is introduced. Different natural language processing methods were applied to pre-process a corpus of hotel descriptions. Further, three machine learning approaches for the allocation of hotel descriptions to travel behavioural patterns were implemented: clustering, classification and a dictionary-based approach. The main results show that clustering cannot be used in this context since the algorithm mostly relies on the operator-dependent structure of the descriptions. Supervised classification achieves the highest precision for six travel patterns, whereas the dictionary approach works best for one pattern. In general, the results for the different travel patterns vary due to the unequally distributed data sets as well as various characteristics of the patterns.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The amount of people using online platforms to book a travel accommodation has grown tremendously. Hence, tour operators implement recommender systems to offer most suitable hotels to their customers. In this paper, a method of using hotel descriptions for recommendation is introduced. Different natural language processing methods were applied to pre-process a corpus of hotel descriptions. Further, three machine learning approaches for the allocation of hotel descriptions to travel behavioural patterns were implemented: clustering, classification and a dictionary-based approach. The main results show that clustering cannot be used in this context since the algorithm mostly relies on the operator-dependent structure of the descriptions. Supervised classification achieves the highest precision for six travel patterns, whereas the dictionary approach works best for one pattern. In general, the results for the different travel patterns vary due to the unequally distributed data sets as well as various characteristics of the patterns.
Grossmann, Wilfried; Sertkan, Mete; Neidhardt, Julia; Werthner, Hannes
Pictures as a tool for matching tourist preferences with destinations. Book Section
In: Augstein, Mirjam; Herder, Eelco; Wörndl, Wolfgang (Ed.): Personalized Human-Computer Interaction., pp. 1–5, DeGruyter, Oldenbourg, 2018.
@incollection{ 20.500.12708_29973,
title = {Pictures as a tool for matching tourist preferences with destinations.},
author = {Wilfried Grossmann and Mete Sertkan and Julia Neidhardt and Hannes Werthner},
editor = {Mirjam Augstein and Eelco Herder and Wolfgang Wörndl},
year = {2018},
date = {2018-01-01},
booktitle = {Personalized Human-Computer Interaction.},
pages = {1–5},
publisher = {DeGruyter},
address = {Oldenbourg},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
2017
Delic, Amra; Neidhardt, Julia
A Comprehensive Approach to Group Recommendations in the Travel and Tourism Domain Proceedings Article
In: Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization, ACM, New York, 2017.
@inproceedings{ 20.500.12708_57166,
title = {A Comprehensive Approach to Group Recommendations in the Travel and Tourism Domain},
author = {Amra Delic and Julia Neidhardt},
doi = {10.1145/3099023.3099076},
year = {2017},
date = {2017-01-01},
booktitle = {Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization},
publisher = {ACM},
address = {New York},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Neidhardt, Julia; Fesenmaier, Daniel R.; Kuflik, Tsvi; Wörndl, Wolfgang
RecTour 2017 Proceedings Article
In: Proceedings of the Eleventh ACM Conference on Recommender Systems, ACM, New York, NY, USA, 2017.
@inproceedings{ 20.500.12708_57172,
title = {RecTour 2017},
author = {Julia Neidhardt and Daniel R. Fesenmaier and Tsvi Kuflik and Wolfgang Wörndl},
doi = {10.1145/3109859.3109962},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings of the Eleventh ACM Conference on Recommender Systems},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Grün, Christoph; Neidhardt, Julia; Werthner, Hannes
Ontology-based Matchmaking to Provide Personalized Recommendations for Tourists Proceedings Article
In: ENTER Conference, Information and Communication Technologies in Tourism 2017, pp. 3–14, Springer, 2017, ISBN: 978-3-319-51167-2.
@inproceedings{ 20.500.12708_56750,
title = {Ontology-based Matchmaking to Provide Personalized Recommendations for Tourists},
author = {Christoph Grün and Julia Neidhardt and Hannes Werthner},
isbn = {978-3-319-51167-2},
year = {2017},
date = {2017-01-01},
booktitle = {ENTER Conference, Information and Communication Technologies in Tourism 2017},
pages = {3–14},
publisher = {Springer},
abstract = {This paper addresses the challenges to support tourists in their decision-making during the pre-trip phase and to facilitate the process of identifying those tourism objects that best fit the tourists´ preferences. The latter directly depends on the quality of the matchmaking process, i.e. finding those tourism objects that are most attractive to a particular tourist. To achieve this goal, an innovative approach is introduced that matches tourist profiles with the characteristics of tourism objects in order to obtain a ranked list of appropriate objects for a particular tourist. The matchmaking process leverages tourist factors as a shortcut to propose a first user profile and related to this, a first set of tourism objects. User feedback is then used to dynamically adapt the tourist profile and thus refine the set of recommended objects. Our approach is tested through a prototypical recommender system that suggests tourists in Vienna attractions that are tailored to their personal needs. Furthermore, a user study is conducted by asking people to interact with the system and fill in a questionnaire afterwards.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper addresses the challenges to support tourists in their decision-making during the pre-trip phase and to facilitate the process of identifying those tourism objects that best fit the tourists´ preferences. The latter directly depends on the quality of the matchmaking process, i.e. finding those tourism objects that are most attractive to a particular tourist. To achieve this goal, an innovative approach is introduced that matches tourist profiles with the characteristics of tourism objects in order to obtain a ranked list of appropriate objects for a particular tourist. The matchmaking process leverages tourist factors as a shortcut to propose a first user profile and related to this, a first set of tourism objects. User feedback is then used to dynamically adapt the tourist profile and thus refine the set of recommended objects. Our approach is tested through a prototypical recommender system that suggests tourists in Vienna attractions that are tailored to their personal needs. Furthermore, a user study is conducted by asking people to interact with the system and fill in a questionnaire afterwards.
Neidhardt, Julia; Werthner, Hannes
Travellers and Their Joint Characteristics Within the Seven-Factor Model Proceedings Article
In: ENTER Conference, Information and Communication Technologies in Tourism 2017, pp. 503–515, Springer, 2017, ISBN: 978-3-319-51167-2.
@inproceedings{ 20.500.12708_56751,
title = {Travellers and Their Joint Characteristics Within the Seven-Factor Model},
author = {Julia Neidhardt and Hannes Werthner},
isbn = {978-3-319-51167-2},
year = {2017},
date = {2017-01-01},
booktitle = {ENTER Conference, Information and Communication Technologies in Tourism 2017},
pages = {503–515},
publisher = {Springer},
abstract = {Recommender systems face specific challenges in the travel domain, as the tourism product is typically very complex. In addition, travelling can be seen as an emotional experience. Thus travel decisions are usually not only based on rational criteria but are rather implicitly given. Therefore sophisticated user models are required. In this paper it is analysed in detail whether the seven-factor model is capable of differentiating between different groups of users in an accurate way. Within this model each user is described with respect to seven travel behavioural patterns that account for both tourist roles and personality traits of a user. To identify groups of travellers, individual attributes are used and also a cluster analysis is conducted. With the help of statistical analyses clear evidence is provided that the seven-factor model is capable of distinguishing between different groups of users in a meaningful and effective way.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Recommender systems face specific challenges in the travel domain, as the tourism product is typically very complex. In addition, travelling can be seen as an emotional experience. Thus travel decisions are usually not only based on rational criteria but are rather implicitly given. Therefore sophisticated user models are required. In this paper it is analysed in detail whether the seven-factor model is capable of differentiating between different groups of users in an accurate way. Within this model each user is described with respect to seven travel behavioural patterns that account for both tourist roles and personality traits of a user. To identify groups of travellers, individual attributes are used and also a cluster analysis is conducted. With the help of statistical analyses clear evidence is provided that the seven-factor model is capable of distinguishing between different groups of users in a meaningful and effective way.
Delic, Amra; Neidhardt, Julia; Rook, Laurens; Werthner, Hannes; Zanker, Markus
Researching Individual Satisfaction with Group Decisions in Tourism: Experimental Evidence Proceedings Article
In: ENTER Conference, Information and Communication Technologies in Tourism 2017, pp. 73–84, Springer, 2017, ISBN: 978-3-319-51167-2.
@inproceedings{ 20.500.12708_56749b,
title = {Researching Individual Satisfaction with Group Decisions in Tourism: Experimental Evidence},
author = {Amra Delic and Julia Neidhardt and Laurens Rook and Hannes Werthner and Markus Zanker},
isbn = {978-3-319-51167-2},
year = {2017},
date = {2017-01-01},
booktitle = {ENTER Conference, Information and Communication Technologies in Tourism 2017},
pages = {73–84},
publisher = {Springer},
abstract = {The goal of the present study was to investigate how satisfied individuals are with the final outcome of a group decision-making process on a joint travel destination. Using an experimental paradigm (N_total= 200},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The goal of the present study was to investigate how satisfied individuals are with the final outcome of a group decision-making process on a joint travel destination. Using an experimental paradigm (N_total= 200
Neidhardt, Julia; Rümmele, Nataliia; Werthner, Hannes
Predicting happiness: user interactions and sentiment analysis in an online travel forum Journal Article
In: Information Technology & Tourism, vol. 17, iss. 1, pp. 101–119, 2017, ISSN: 1098-3058.
@article{ 20.500.12708_50b,
title = {Predicting happiness: user interactions and sentiment analysis in an online travel forum},
author = {Julia Neidhardt and Nataliia Rümmele and Hannes Werthner},
doi = {10.1007/s40558-017-0079-2},
issn = {1098-3058},
year = {2017},
date = {2017-01-01},
journal = {Information Technology & Tourism},
volume = {17},
issue = {1},
pages = {101–119},
publisher = {SPRINGER HEIDELBERG},
abstract = {Web sources of tourism services provide valuable resources of knowledge not only for the travellers but also for the companies. Tourism operators are increasingly aware that user related data should be regarded as an important asset. Furthermore, as data is permanently generated and always available, the landscape of empirical research is changing. In this paper, user activities and interactions in the tourism domain are analysed. In particular, the emotions of the users regarding their forthcoming trips are studied with the objective to characterize interdependencies between them. Social network analysis is applied to examine interactions between the users. To capture their emotions, text mining techniques and sentiment analysis are applied to construct a measure, which is based on free-text comments in a travel forum. The experimental outcome provides some evidence that the network has an effect on the sentiment of the users.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Web sources of tourism services provide valuable resources of knowledge not only for the travellers but also for the companies. Tourism operators are increasingly aware that user related data should be regarded as an important asset. Furthermore, as data is permanently generated and always available, the landscape of empirical research is changing. In this paper, user activities and interactions in the tourism domain are analysed. In particular, the emotions of the users regarding their forthcoming trips are studied with the objective to characterize interdependencies between them. Social network analysis is applied to examine interactions between the users. To capture their emotions, text mining techniques and sentiment analysis are applied to construct a measure, which is based on free-text comments in a travel forum. The experimental outcome provides some evidence that the network has an effect on the sentiment of the users.
Grill, Gabriel; Neidhardt, Julia; Werthner, Hannes
Network Analysis on the Austrian Media Corpus Proceedings Article
In: VSS 2017 – Vienna young Scientists Symposium, pp. 128–129, Book-of-Abstracts.com, Heinz A. Krebs, Gumpoldskirchen, Austria, 2017, ISBN: 978-3-9504017-2-1.
@inproceedings{ 20.500.12708_57171b,
title = {Network Analysis on the Austrian Media Corpus},
author = {Gabriel Grill and Julia Neidhardt and Hannes Werthner},
isbn = {978-3-9504017-2-1},
year = {2017},
date = {2017-01-01},
booktitle = {VSS 2017 - Vienna young Scientists Symposium},
pages = {128–129},
publisher = {Book-of-Abstracts.com},
address = {Heinz A. Krebs, Gumpoldskirchen, Austria},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2016
Neidhardt, Julia; Rümmele, Nataliia; Werthner, Hannes
Can We Predict Your Sentiments by Listening to Your Peers? Proceedings Article
In: Information and Communication Technologies in Tourism 2016, pp. 593–603, Springer International Publishing, Part V, 2016, ISBN: 9783319282312.
@inproceedings{ 20.500.12708_56265,
title = {Can We Predict Your Sentiments by Listening to Your Peers?},
author = {Julia Neidhardt and Nataliia Rümmele and Hannes Werthner},
doi = {10.1007/978-3-319-28231-2_43},
isbn = {9783319282312},
year = {2016},
date = {2016-01-01},
booktitle = {Information and Communication Technologies in Tourism 2016},
pages = {593–603},
publisher = {Springer International Publishing},
address = {Part V},
abstract = {Web sources of tourism services provide valuable resources of knowledge not only for the travellers but also for the companies. Tourism operators are increasingly aware that user related data should be regarded as an important asset. In this paper, user activities and interactions in the tourism domain are analysed. In particular, the emotions of the users regarding their forthcoming trips are studied with the objective to characterize interdependencies between them. Social network analysis is applied to characterize the interactions between the users. To capture their emotions, text mining techniques and sentiment analysis are applied to construct a measure, which is based on free-text comments in a travel forum. The experimental outcome provides some evidence that social influence between the users in the network exists.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Web sources of tourism services provide valuable resources of knowledge not only for the travellers but also for the companies. Tourism operators are increasingly aware that user related data should be regarded as an important asset. In this paper, user activities and interactions in the tourism domain are analysed. In particular, the emotions of the users regarding their forthcoming trips are studied with the objective to characterize interdependencies between them. Social network analysis is applied to characterize the interactions between the users. To capture their emotions, text mining techniques and sentiment analysis are applied to construct a measure, which is based on free-text comments in a travel forum. The experimental outcome provides some evidence that social influence between the users in the network exists.
Delic, Amra; Neidhardt, Julia; Werthner, Hannes
Are Sun Lovers nervous? Proceedings Article
In: ENTER 2016: Volume 7, e-Review of Tourism Research, 2016.
@inproceedings{ 20.500.12708_56264,
title = {Are Sun Lovers nervous?},
author = {Amra Delic and Julia Neidhardt and Hannes Werthner},
year = {2016},
date = {2016-01-01},
booktitle = {ENTER 2016: Volume 7},
publisher = {e-Review of Tourism Research},
abstract = {In the travel and tourism industry, understanding travellers´ behaviours, needs and interests is one of the major issues to be tackled in order to provide excellent services. During the last decades, enormous efforts have been made in numerous studies with regard to the topic. The goal of this paper is to contribute to this knowledge base, trying to find relationships between tourist roles and long term personality traits. The paper is based on the 17 tourist roles defined by Gibson and Yiannakis (2002) and the Big Five Factors describing personality traits. Data collection was done using a 50 items questionnaire capturing basic demographic data, travel preferences and personality traits of nearly 1.000 respondents. The analysis shows interesting results, especially when taking different age ranges into consideration.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In the travel and tourism industry, understanding travellers´ behaviours, needs and interests is one of the major issues to be tackled in order to provide excellent services. During the last decades, enormous efforts have been made in numerous studies with regard to the topic. The goal of this paper is to contribute to this knowledge base, trying to find relationships between tourist roles and long term personality traits. The paper is based on the 17 tourist roles defined by Gibson and Yiannakis (2002) and the Big Five Factors describing personality traits. Data collection was done using a 50 items questionnaire capturing basic demographic data, travel preferences and personality traits of nearly 1.000 respondents. The analysis shows interesting results, especially when taking different age ranges into consideration.
Fesenmaier, Daniel R.; Kuflik, Tsvi; Neidhardt, Julia
RecTour 2016 Proceedings Article
In: Proceedings of the 10th ACM Conference on Recommender Systems, ACM, 2016.
@inproceedings{ 20.500.12708_56513,
title = {RecTour 2016},
author = {Daniel R. Fesenmaier and Tsvi Kuflik and Julia Neidhardt},
doi = {10.1145/2959100.2959205},
year = {2016},
date = {2016-01-01},
booktitle = {Proceedings of the 10th ACM Conference on Recommender Systems},
publisher = {ACM},
abstract = {In this paper, we summarize RecTour 2016 – a workshop on recommenders in tourism co-located with RecSys 2016. There was a great variety of submissions, i.e., research papers, demo papers and position papers, addressing fundamental challenges of recommender systems in the tourism domain. The main topics included group recommendations, context-aware recommenders, choice-based recommenders and event recommendations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we summarize RecTour 2016 – a workshop on recommenders in tourism co-located with RecSys 2016. There was a great variety of submissions, i.e., research papers, demo papers and position papers, addressing fundamental challenges of recommender systems in the tourism domain. The main topics included group recommendations, context-aware recommenders, choice-based recommenders and event recommendations.
Delic, Amra; Neidhardt, Julia; Nguyen, Thuy Ngoc; Ricci, Francesco; Rook, Laurens; Werthner, Hannes; Zanker, Markus
Observing Group Decision Making Processes Proceedings Article
In: Proceedings of the 10th ACM Conference on Recommender Systems, ACM, 2016.
@inproceedings{ 20.500.12708_56514,
title = {Observing Group Decision Making Processes},
author = {Amra Delic and Julia Neidhardt and Thuy Ngoc Nguyen and Francesco Ricci and Laurens Rook and Hannes Werthner and Markus Zanker},
doi = {10.1145/2959100.2959168},
year = {2016},
date = {2016-01-01},
booktitle = {Proceedings of the 10th ACM Conference on Recommender Systems},
publisher = {ACM},
abstract = {Most research on group recommender systems relies on the assumption that individuals have conflicting preferences; in order to generate group recommendations the system should identify a fair way of aggregating these preferences. Both empirical studies and theoretical frameworks have tried to identify the most effective preference aggregation techniques without coming to definite conclusions. In this paper, we propose to approach group recommendation from the group dynamics perspective and analyze the group decision making process for a particular task (in the travel domain). We observe several individual and group properties and correlate them to choice satisfaction. Supported by these initial results we therefore advocate for the development of new group recommendation techniques that consider group dynamics and support the full group decision making process.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Most research on group recommender systems relies on the assumption that individuals have conflicting preferences; in order to generate group recommendations the system should identify a fair way of aggregating these preferences. Both empirical studies and theoretical frameworks have tried to identify the most effective preference aggregation techniques without coming to definite conclusions. In this paper, we propose to approach group recommendation from the group dynamics perspective and analyze the group decision making process for a particular task (in the travel domain). We observe several individual and group properties and correlate them to choice satisfaction. Supported by these initial results we therefore advocate for the development of new group recommendation techniques that consider group dynamics and support the full group decision making process.
Delic, Amra; Neidhardt, Julia; Nguyen, Thuy Ngoc; Ricci, Francesco
Research Methods for Group Recommender Systems Proceedings Article
In: Proceedings of the Workshop on Recommenders in Tourism (RecTour 2016), pp. 30–37, CEUR-WS.org, Boston, MA, USA, 2016.
@inproceedings{ 20.500.12708_56515,
title = {Research Methods for Group Recommender Systems},
author = {Amra Delic and Julia Neidhardt and Thuy Ngoc Nguyen and Francesco Ricci},
year = {2016},
date = {2016-01-01},
booktitle = {Proceedings of the Workshop on Recommenders in Tourism (RecTour 2016)},
pages = {30–37},
publisher = {CEUR-WS.org},
address = {Boston, MA, USA},
series = {CEUR Workshop Proceedings},
abstract = {In this article we argue that the research on group recom- mender systems must look more carefully at group dynamics in decision making in order to produce technologies that will be truly beneficial for users. Hence, we illustrate a user study method aimed at observing and measuring the evolution of user preferences and actions in a tourism decision making task: finding a destination to visit. We discuss the benefits and caveats of such an observational study method and we present the implications that the derived data and findings may have on the design of interactive group recommender systems.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this article we argue that the research on group recom- mender systems must look more carefully at group dynamics in decision making in order to produce technologies that will be truly beneficial for users. Hence, we illustrate a user study method aimed at observing and measuring the evolution of user preferences and actions in a tourism decision making task: finding a destination to visit. We discuss the benefits and caveats of such an observational study method and we present the implications that the derived data and findings may have on the design of interactive group recommender systems.
Neidhardt, Julia
Modeling and understanding social influence in groups and networks PhD Thesis
Technische Universität Wien, 2016.
@phdthesis{ 20.500.12708_2430,
title = {Modeling and understanding social influence in groups and networks},
author = {Julia Neidhardt},
doi = {10.34726/hss.2016.37208},
year = {2016},
date = {2016-01-01},
address = {Wien},
school = {Technische Universität Wien},
abstract = {Social influence occurs when a person changes her behavior according to the behavior of other people in the social system. Today, these complex mechanisms can be studied by making use of vast amounts of detailed data on human behavior and social interactions, coming from the World Wide Web and other data sources. The main objective of this work is to capture social influence processes in computational models on a large scale. In the presented analysis, three levels of information are distinguished (i.e., individual, group and network level). To illustrate each level in detail and to show their differences, conventional methods and their shortcomings are discussed and empirical studies are conducted. At the individual level, regression models are applied; at the group level, approaches based on geometric data analysis; and at the network level, social network analysis. At the network level, conditional random field models are introduced as an alternative way to capture social influence processes. Finally, it is discussed, how all three levels can be integrated into one model. The empirical analyses are related to travel recommender systems, churn behavior, sentiments in online forums and team-vs-team competitions. The results of this belong to two categories: 1) methodological advances; 2) concrete statements in different domains of application. It is shown that the introduced models are able to capture social context in an accurate way. Most of them, moreover, scale well. Furthermore, integrating different levels of information allows comparing them and their associations with the studied social influence processes directly. Thus, a more comprehensive picture of the respective domain of application is obtained.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Social influence occurs when a person changes her behavior according to the behavior of other people in the social system. Today, these complex mechanisms can be studied by making use of vast amounts of detailed data on human behavior and social interactions, coming from the World Wide Web and other data sources. The main objective of this work is to capture social influence processes in computational models on a large scale. In the presented analysis, three levels of information are distinguished (i.e., individual, group and network level). To illustrate each level in detail and to show their differences, conventional methods and their shortcomings are discussed and empirical studies are conducted. At the individual level, regression models are applied; at the group level, approaches based on geometric data analysis; and at the network level, social network analysis. At the network level, conditional random field models are introduced as an alternative way to capture social influence processes. Finally, it is discussed, how all three levels can be integrated into one model. The empirical analyses are related to travel recommender systems, churn behavior, sentiments in online forums and team-vs-team competitions. The results of this belong to two categories: 1) methodological advances; 2) concrete statements in different domains of application. It is shown that the introduced models are able to capture social context in an accurate way. Most of them, moreover, scale well. Furthermore, integrating different levels of information allows comparing them and their associations with the studied social influence processes directly. Thus, a more comprehensive picture of the respective domain of application is obtained.
2015
Neidhardt, Julia; Huang, Yun; Werthner, Hannes; Contractor, Noshir
Conditional Random Field Models as a Way to Capture Peer Influence in Social Networks Miscellaneous
2015.
@misc{ 20.500.12708_86041,
title = {Conditional Random Field Models as a Way to Capture Peer Influence in Social Networks},
author = {Julia Neidhardt and Yun Huang and Hannes Werthner and Noshir Contractor},
year = {2015},
date = {2015-01-01},
abstract = {Peer influence occurs when individuals adapt their behavior according to the behavior of their friends. When studying human interactions and the spreading of beliefs, feelings or behaviors, influence mechanisms typically play a decisive role. If there are multiple observations of network and behavior, temporal models such as SIENA can identify social influence based on behavioral change at different time points. However, in cross-sectional cases, where only one observation of the network is available, studying and predicting individual behavior while controlling for social influence is very challenging both statistically and computationally. In this work, we propose using Conditional Random Field (CRF) logistic regression for modeling peer influence in cross-sectional settings and compare it with existing methods such as Autologistic Actor Attribute Models (ALAAM).
We use data about teenage smoking behavior from previous social influence studies to evaluate our approach. The results of CRF models are consistent with ALAAM. CRF produces accurate coefficient estimations compared to the over-estimation in ordinary logistic regression models. For example, after controlling for contagion effects, gender has no significant impact on smoking; but it has in the ordinary logistics regression. Similarly, drinking alcohol, smoking siblings, and being in a romantic relationship have smaller effect sizes when social influence effects are taken into account. This study shows that CRF models are capable of modeling individual behavior with peer influence and are both computationally efficient and scalable for large networks. Moreover, the extension of the CRF models can characterize different types of peer influence such as contagion and similarity and can model dynamic behavior in a network.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Peer influence occurs when individuals adapt their behavior according to the behavior of their friends. When studying human interactions and the spreading of beliefs, feelings or behaviors, influence mechanisms typically play a decisive role. If there are multiple observations of network and behavior, temporal models such as SIENA can identify social influence based on behavioral change at different time points. However, in cross-sectional cases, where only one observation of the network is available, studying and predicting individual behavior while controlling for social influence is very challenging both statistically and computationally. In this work, we propose using Conditional Random Field (CRF) logistic regression for modeling peer influence in cross-sectional settings and compare it with existing methods such as Autologistic Actor Attribute Models (ALAAM).
We use data about teenage smoking behavior from previous social influence studies to evaluate our approach. The results of CRF models are consistent with ALAAM. CRF produces accurate coefficient estimations compared to the over-estimation in ordinary logistic regression models. For example, after controlling for contagion effects, gender has no significant impact on smoking; but it has in the ordinary logistics regression. Similarly, drinking alcohol, smoking siblings, and being in a romantic relationship have smaller effect sizes when social influence effects are taken into account. This study shows that CRF models are capable of modeling individual behavior with peer influence and are both computationally efficient and scalable for large networks. Moreover, the extension of the CRF models can characterize different types of peer influence such as contagion and similarity and can model dynamic behavior in a network.
We use data about teenage smoking behavior from previous social influence studies to evaluate our approach. The results of CRF models are consistent with ALAAM. CRF produces accurate coefficient estimations compared to the over-estimation in ordinary logistic regression models. For example, after controlling for contagion effects, gender has no significant impact on smoking; but it has in the ordinary logistics regression. Similarly, drinking alcohol, smoking siblings, and being in a romantic relationship have smaller effect sizes when social influence effects are taken into account. This study shows that CRF models are capable of modeling individual behavior with peer influence and are both computationally efficient and scalable for large networks. Moreover, the extension of the CRF models can characterize different types of peer influence such as contagion and similarity and can model dynamic behavior in a network.
Neidhardt, Julia
Computational Analyses of Network Data Miscellaneous
2015.
@misc{ 20.500.12708_86175,
title = {Computational Analyses of Network Data},
author = {Julia Neidhardt},
year = {2015},
date = {2015-01-01},
abstract = {In this sessions we will use software tools to analyze network data, where we will give equal emphasis to conducting the analysis and interpreting the results.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
In this sessions we will use software tools to analyze network data, where we will give equal emphasis to conducting the analysis and interpreting the results.
Huang, Yun; Neidhardt, Julia
From Networks to Space: Constructing Metric Spaces for Social Interactions Miscellaneous
2015.
@misc{ 20.500.12708_86174,
title = {From Networks to Space: Constructing Metric Spaces for Social Interactions},
author = {Yun Huang and Julia Neidhardt},
year = {2015},
date = {2015-01-01},
abstract = {Bourdieu's field theory provides a relational framework to bridge objective ties and subjective relations in complex social systems. The important concepts, field and habitus, provide essential building blocks for constructing social space. Although field theory has been tested in various social settings, many of them only focused on a particular domain of social structures and avoid the nature of multi-dimension and overlapping social structures. On the other hand, the advancement of online social communities such as Facebook and online games has generated enormous network data reflecting the underlying social interactions. This provides opportunities and challenges to study intertwisted social groups and illustrate the structure of a much larger social space.
Despite of his advocacy of relational thinking, Bourdieu argued against social network analysis based on individual exchange and interactions and preferred correspondence analysis, which concentrates on objective relations, e.g. differential levels of capitals. Nooy (2003) compared correspondence analysis and social network analysis and argued that objective relations and individual interactions have a mutual influence and both should be used for identifying people's positions in the social space. The recent progress of Exponential Random Graph Models (ERGM/p*) provides advanced techniques to extract underlying formation mechanisms (part of habitus) from the structures of observed individual interactions. However, due to the computational complexity, this method is only feasible for small and homogenous networks.
In this paper, we propose hyperbolic embedding as a nexus to integrate field theory and social network analysis. As type of geometric data analysis, hyperbolic embedding supports more flexible dimensional reduction and eliminates the 2D restriction of correspondence analysis; meanwhile, as Krioukov et al. (2010) have shown, hyperbolic embedding also characterizes the link probability in exponential random graphs. Therefore, we obtain a unified metric space (through hyperbolic embedding) that represents an ensemble of capitals and interactions and provides positions of individuals and their distances in social space. To demonstrate the method, we use large networks from online communities such as Second Life to construct a metric space of hundreds of thousands people and illustrate the shapes of local structures.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Bourdieu’s field theory provides a relational framework to bridge objective ties and subjective relations in complex social systems. The important concepts, field and habitus, provide essential building blocks for constructing social space. Although field theory has been tested in various social settings, many of them only focused on a particular domain of social structures and avoid the nature of multi-dimension and overlapping social structures. On the other hand, the advancement of online social communities such as Facebook and online games has generated enormous network data reflecting the underlying social interactions. This provides opportunities and challenges to study intertwisted social groups and illustrate the structure of a much larger social space.
Despite of his advocacy of relational thinking, Bourdieu argued against social network analysis based on individual exchange and interactions and preferred correspondence analysis, which concentrates on objective relations, e.g. differential levels of capitals. Nooy (2003) compared correspondence analysis and social network analysis and argued that objective relations and individual interactions have a mutual influence and both should be used for identifying people’s positions in the social space. The recent progress of Exponential Random Graph Models (ERGM/p*) provides advanced techniques to extract underlying formation mechanisms (part of habitus) from the structures of observed individual interactions. However, due to the computational complexity, this method is only feasible for small and homogenous networks.
In this paper, we propose hyperbolic embedding as a nexus to integrate field theory and social network analysis. As type of geometric data analysis, hyperbolic embedding supports more flexible dimensional reduction and eliminates the 2D restriction of correspondence analysis; meanwhile, as Krioukov et al. (2010) have shown, hyperbolic embedding also characterizes the link probability in exponential random graphs. Therefore, we obtain a unified metric space (through hyperbolic embedding) that represents an ensemble of capitals and interactions and provides positions of individuals and their distances in social space. To demonstrate the method, we use large networks from online communities such as Second Life to construct a metric space of hundreds of thousands people and illustrate the shapes of local structures.
Despite of his advocacy of relational thinking, Bourdieu argued against social network analysis based on individual exchange and interactions and preferred correspondence analysis, which concentrates on objective relations, e.g. differential levels of capitals. Nooy (2003) compared correspondence analysis and social network analysis and argued that objective relations and individual interactions have a mutual influence and both should be used for identifying people’s positions in the social space. The recent progress of Exponential Random Graph Models (ERGM/p*) provides advanced techniques to extract underlying formation mechanisms (part of habitus) from the structures of observed individual interactions. However, due to the computational complexity, this method is only feasible for small and homogenous networks.
In this paper, we propose hyperbolic embedding as a nexus to integrate field theory and social network analysis. As type of geometric data analysis, hyperbolic embedding supports more flexible dimensional reduction and eliminates the 2D restriction of correspondence analysis; meanwhile, as Krioukov et al. (2010) have shown, hyperbolic embedding also characterizes the link probability in exponential random graphs. Therefore, we obtain a unified metric space (through hyperbolic embedding) that represents an ensemble of capitals and interactions and provides positions of individuals and their distances in social space. To demonstrate the method, we use large networks from online communities such as Second Life to construct a metric space of hundreds of thousands people and illustrate the shapes of local structures.
Neidhardt, Julia; Huang, Yun; Contractor, Noshir
Team vs. Team: Success Factors in a Multiplayer Online Battle Arena Game Proceedings Article
In: Academy of Management Proceedings, 2015.
@inproceedings{ 20.500.12708_56043,
title = {Team vs. Team: Success Factors in a Multiplayer Online Battle Arena Game},
author = {Julia Neidhardt and Yun Huang and Noshir Contractor},
doi = {10.5465/ambpp.2015.18725abstract},
year = {2015},
date = {2015-01-01},
booktitle = {Academy of Management Proceedings},
series = {Academy of Management Proceedings},
abstract = {There is a small but growing body of research investigating how teams form and how that affects how they perform. Much of that research focuses on teams that seek to accomplish certain tasks such as writing an article or perform a Broadway musical. There has been much less investigation of the relative performance of teams that form to directly compete against another team. In this study, we report on team-vs-team competitions in the multiplayer online game Dota 2. Here, the teams´ overall goal is to beat the opponent. We use this unique setting to observe multi-level factors influence the relative performance of the teams. Those factors include compositional factors or attributes of the individuals comprising a team, relational factors or prior relations among individuals within a team and ecosystem factors or overlapping prior membership of team members with others within the ecosystem of teams. We also study how these multilevel factors affect the duration of a match. Our results show that advantages at the compositional, relational and ecosystem levels predict which team will succeed in short or medium duration matches. Relational and ecosystem factors are particularly helpful in predicting the winner in short duration matches, whereas compositional factors are more important predicting winners in medium duration matches. However, the two types of relations have opposite effects on the duration of winning. None of the three multilevel factors help explain which team will win in long matches.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
There is a small but growing body of research investigating how teams form and how that affects how they perform. Much of that research focuses on teams that seek to accomplish certain tasks such as writing an article or perform a Broadway musical. There has been much less investigation of the relative performance of teams that form to directly compete against another team. In this study, we report on team-vs-team competitions in the multiplayer online game Dota 2. Here, the teams´ overall goal is to beat the opponent. We use this unique setting to observe multi-level factors influence the relative performance of the teams. Those factors include compositional factors or attributes of the individuals comprising a team, relational factors or prior relations among individuals within a team and ecosystem factors or overlapping prior membership of team members with others within the ecosystem of teams. We also study how these multilevel factors affect the duration of a match. Our results show that advantages at the compositional, relational and ecosystem levels predict which team will succeed in short or medium duration matches. Relational and ecosystem factors are particularly helpful in predicting the winner in short duration matches, whereas compositional factors are more important predicting winners in medium duration matches. However, the two types of relations have opposite effects on the duration of winning. None of the three multilevel factors help explain which team will win in long matches.
Sacharidis, Dimitrios; Delic, Amra; Neidhardt, Julia
Learning the Role and Behavior of Users in Group Decision Making Proceedings Article
In: Mouzhi, Ge; Ricci, Francesco (Ed.): Proceedings of the 2nd International Workshop on Decision Making and Recommender Systems, pp. 25–28, CEUR-WS.org, 2015.
@inproceedings{ 20.500.12708_56269,
title = {Learning the Role and Behavior of Users in Group Decision Making},
author = {Dimitrios Sacharidis and Amra Delic and Julia Neidhardt},
editor = {Ge Mouzhi and Francesco Ricci},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 2nd International Workshop on Decision Making and Recommender Systems},
pages = {25–28},
publisher = {CEUR-WS.org},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Neidhardt, Julia; Pobiedina, Nataliia; Werthner, Hannes
What Can We Learn From Review Data? Proceedings Article
In: ENTER 2015: Volume 6, e-Review of Tourism Research, 2015.
@inproceedings{ 20.500.12708_55856,
title = {What Can We Learn From Review Data?},
author = {Julia Neidhardt and Nataliia Pobiedina and Hannes Werthner},
year = {2015},
date = {2015-01-01},
booktitle = {ENTER 2015: Volume 6},
publisher = {e-Review of Tourism Research},
abstract = {Online reviews of tourism services provide valuable resources of knowledge not only for travelers but also for companies. Tourism operators are more and more aware that user related data should be seen as an important asset. This work-in-progress analyzes free text reviews as well as numerical ratings of group tours with the aim to characterize their relations. This is done with the help of statistical models. On the one hand, these models comprise textual attributes and sentiment scores of the reviews, based on text mining techniques and sentiment analysis respectively. On the other hand, non-textual attributes such as meta data about the tours and user related factors are included. First results imply a very moderate relationship between sentiment scores and ratings; the non-textual attributes appear to have a higher impact.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Online reviews of tourism services provide valuable resources of knowledge not only for travelers but also for companies. Tourism operators are more and more aware that user related data should be seen as an important asset. This work-in-progress analyzes free text reviews as well as numerical ratings of group tours with the aim to characterize their relations. This is done with the help of statistical models. On the one hand, these models comprise textual attributes and sentiment scores of the reviews, based on text mining techniques and sentiment analysis respectively. On the other hand, non-textual attributes such as meta data about the tours and user related factors are included. First results imply a very moderate relationship between sentiment scores and ratings; the non-textual attributes appear to have a higher impact.
Krathu, Worarat; Pichler, Christian; Xiao, Guohui; Werthner, Hannes; Neidhardt, Julia; Zapletal, Marco; Huemer, Christian
Inter-organizational success factors: a cause and effect model Journal Article
In: Information Systems and E-Business Management, vol. 13, iss. 3, pp. 553–593, 2015, ISSN: 1617-9846.
@article{ 20.500.12708_150395,
title = {Inter-organizational success factors: a cause and effect model},
author = {Worarat Krathu and Christian Pichler and Guohui Xiao and Hannes Werthner and Julia Neidhardt and Marco Zapletal and Christian Huemer},
doi = {10.1007/s10257-014-0258-z},
issn = {1617-9846},
year = {2015},
date = {2015-01-01},
journal = {Information Systems and E-Business Management},
volume = {13},
issue = {3},
pages = {553–593},
abstract = {Inter-organizational systems form the basis for successful business collaboration in the Internet and B2B e-commerce era. To properly design and manage such systems one needs to understand the structure and dynamics of the relationships between organizations. The evaluation of such inter-organizational relationships (IORs) is normally conducted using "success factors". These are often referred to as constructs, such as trust and information sharing. In strategic management and performance analysis, different methods are employed for evaluating business performance and strategies, such as the Balanced Scorecard (BSC) method. The BSC utilizes success factors for measuring and monitoring IORs against business strategies. For these reasons, a thorough understanding of success factors, the relationships between them, as well as their relationship to business strategies is required. In other words, understanding success factors allows strategists deriving measurements for success factors as well as aligning these success factors with business strategies. This underpins nowadays close relationship between business strategy, IORs and their realization by means of inter-organizational systems. In this paper, we present (1) a systematic literature review studying success factors and their impact on IORs as well as (2) an analysis of the results found. The review is based on 177 publications, published between 2000 and 2012, dealing with factors influencing IORs. The work presented provides an overview on success factors, influencing relationships between success factors, as well as their influence on the success of IORs. The work is somehow "meta-empirical" as it only looks at published studies and not on own cases. Consequently, it is based on the assumption that studies in scientific literature represent the real-world. The constructs and relationships found in the review are grouped based on their scope and summarized in a cause and effect model. The grouping of constructs results in five groups including Relationship Orientation, Relational Norm, Relational Capital, Atmosphere, and Others. Since the cause and effect model represents a directed graph, different network analysis methods may be applied for analyzing the model. In particular, an in- and out-degree analysis is applied on the cause and effect model for detecting the most influencing as well as the most influenced success factors.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Inter-organizational systems form the basis for successful business collaboration in the Internet and B2B e-commerce era. To properly design and manage such systems one needs to understand the structure and dynamics of the relationships between organizations. The evaluation of such inter-organizational relationships (IORs) is normally conducted using “success factors”. These are often referred to as constructs, such as trust and information sharing. In strategic management and performance analysis, different methods are employed for evaluating business performance and strategies, such as the Balanced Scorecard (BSC) method. The BSC utilizes success factors for measuring and monitoring IORs against business strategies. For these reasons, a thorough understanding of success factors, the relationships between them, as well as their relationship to business strategies is required. In other words, understanding success factors allows strategists deriving measurements for success factors as well as aligning these success factors with business strategies. This underpins nowadays close relationship between business strategy, IORs and their realization by means of inter-organizational systems. In this paper, we present (1) a systematic literature review studying success factors and their impact on IORs as well as (2) an analysis of the results found. The review is based on 177 publications, published between 2000 and 2012, dealing with factors influencing IORs. The work presented provides an overview on success factors, influencing relationships between success factors, as well as their influence on the success of IORs. The work is somehow “meta-empirical” as it only looks at published studies and not on own cases. Consequently, it is based on the assumption that studies in scientific literature represent the real-world. The constructs and relationships found in the review are grouped based on their scope and summarized in a cause and effect model. The grouping of constructs results in five groups including Relationship Orientation, Relational Norm, Relational Capital, Atmosphere, and Others. Since the cause and effect model represents a directed graph, different network analysis methods may be applied for analyzing the model. In particular, an in- and out-degree analysis is applied on the cause and effect model for detecting the most influencing as well as the most influenced success factors.
Neidhardt, Julia; Seyfang, Leonhard; Schuster, Rainer; Werthner, Hannes
A picture-based approach to recommender systems Journal Article
In: Information Technology and Tourism, vol. 15, iss. 1, pp. 49–69, 2015, ISSN: 1098-3058.
@article{ 20.500.12708_150411,
title = {A picture-based approach to recommender systems},
author = {Julia Neidhardt and Leonhard Seyfang and Rainer Schuster and Hannes Werthner},
doi = {10.1007/s40558-014-0017-5},
issn = {1098-3058},
year = {2015},
date = {2015-01-01},
journal = {Information Technology and Tourism},
volume = {15},
issue = {1},
pages = {49–69},
abstract = {Due to their complexity, tourism products present major challenges to recommender techniques. Especially the assessment of customer preferences in order to get accurate user profiles is a non-trivial task for several reasons: (a) tourism is an "emotional" experience, which is typically hard to capture by using rational terms; (b) particularly in early phases of a travel decision process, users are not able to explicitly express their preferences; (c) and they are often lacking domain knowledge and thus have difficulties to use the right terminology. In this paper we introduce an alternative, i.e., a picture-based approach, as a new method to implicitly elicit user preferences for tourism products. We develop a model in which a user's travel profile is composed of seven basic factors. The scores of these factors are determined by asking the user to select a number of pictures that are appealing to him or her. The model as well as its implementation into a recommender system are described in detail. First evaluations show that interactions with the system are perceived as inspiring and enjoyable.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Due to their complexity, tourism products present major challenges to recommender techniques. Especially the assessment of customer preferences in order to get accurate user profiles is a non-trivial task for several reasons: (a) tourism is an “emotional” experience, which is typically hard to capture by using rational terms; (b) particularly in early phases of a travel decision process, users are not able to explicitly express their preferences; (c) and they are often lacking domain knowledge and thus have difficulties to use the right terminology. In this paper we introduce an alternative, i.e., a picture-based approach, as a new method to implicitly elicit user preferences for tourism products. We develop a model in which a user’s travel profile is composed of seven basic factors. The scores of these factors are determined by asking the user to select a number of pictures that are appealing to him or her. The model as well as its implementation into a recommender system are described in detail. First evaluations show that interactions with the system are perceived as inspiring and enjoyable.
Werthner, Hannes; Alzua-Sorzabal, Aurkene; Cantoni, Lorenzo; Dickinger, Astrid; Gretzel, Ulrike; Jannach, Dietmar; Neidhardt, Julia; Pröll, Birgit; Ricci, Francesco; Scaglione, Miriam; Stangl, Brigitte; Stock, Oliviero; Zanker, Markus
Future research issues in IT and tourism Journal Article
In: Information Technology and Tourism, vol. 15, iss. 1, pp. 1–15, 2015, ISSN: 1098-3058.
@article{ 20.500.12708_150597,
title = {Future research issues in IT and tourism},
author = {Hannes Werthner and Aurkene Alzua-Sorzabal and Lorenzo Cantoni and Astrid Dickinger and Ulrike Gretzel and Dietmar Jannach and Julia Neidhardt and Birgit Pröll and Francesco Ricci and Miriam Scaglione and Brigitte Stangl and Oliviero Stock and Markus Zanker},
doi = {10.1007/s40558-014-0021-9},
issn = {1098-3058},
year = {2015},
date = {2015-01-01},
journal = {Information Technology and Tourism},
volume = {15},
issue = {1},
pages = {1–15},
abstract = {The objective of this manifesto (as a result of the JITT workshop in June 2014) is to identify a list of pivotal research topics and issues in e-tourism. E-tourism can be seen as everything that happens electronically in the travel and tourism industry/experience; more formally it is defined as the design, implementation and application of IT and ecommerce solutions in the travel and tourism industry as well as the analysis of the impact of the respective technical and economic processes and market structures on all the involved actors and especially on the traveller's experience. In tourism as an "information business", Information Technology has always played an important role since the 1960s with the computerized reservation systems/global distribution systems; these were one of the first world-wide electronic networks. And since the beginning of the Web in the early 1990s, travel and tourism was and is a major application domain for Web-based services. As such, the domain is also a major driver of technological innovation. This manifesto provides guidelines on strategic research issues for the research community, but as such it is also conceived as a basis document for industry and policy makers.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The objective of this manifesto (as a result of the JITT workshop in June 2014) is to identify a list of pivotal research topics and issues in e-tourism. E-tourism can be seen as everything that happens electronically in the travel and tourism industry/experience; more formally it is defined as the design, implementation and application of IT and ecommerce solutions in the travel and tourism industry as well as the analysis of the impact of the respective technical and economic processes and market structures on all the involved actors and especially on the traveller’s experience. In tourism as an “information business”, Information Technology has always played an important role since the 1960s with the computerized reservation systems/global distribution systems; these were one of the first world-wide electronic networks. And since the beginning of the Web in the early 1990s, travel and tourism was and is a major application domain for Web-based services. As such, the domain is also a major driver of technological innovation. This manifesto provides guidelines on strategic research issues for the research community, but as such it is also conceived as a basis document for industry and policy makers.
2014
Neidhardt, Julia; Huang, Yun; Contractor, Noshir
Assembly factors influencing the victor in head to head short duration team competitions in a multiplayer online battle arena game Miscellaneous
2014.
@misc{ 20.500.12708_86039,
title = {Assembly factors influencing the victor in head to head short duration team competitions in a multiplayer online battle arena game},
author = {Julia Neidhardt and Yun Huang and Noshir Contractor},
year = {2014},
date = {2014-01-01},
abstract = {While network approaches are used to study how the assembly of teams impacts their performance, there has been little attention to assess the impact of assembly on the relative performance of two teams in a head to head contest. In this study, we focus specifically on assembly factors that influence performance of short-duration contests in mid-sized teams playing a multiplayer online game, Dota2, where two teams consisting of five players each compete with each other. We determine the attributes and relational factors that help a team to defeat the opponent. Among attributes we consider the players' skills as well as the diversity of their skills and their roles. Relational factors include the friendship relations within a team, previous co-playing experiences of team members as well as the embeddedness of the team, i.e., whether team members belong to a community that often plays together. We use game log data for short matches (under 30 minutes) within Dota2 to empirically test this model. We find that teams with players who have more diverse roles are more likely to win. We also find some evidence that teams consisting of players who have focused on training their fighting skills rather than on non-fighting skills have an advantage. However, when relational factors are included in the model, some skill factors are no longer significant. Instead, friendship ties between team members as well as the embeddedness of the team within the community have a positive impact on the likelihood of a team to win.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
While network approaches are used to study how the assembly of teams impacts their performance, there has been little attention to assess the impact of assembly on the relative performance of two teams in a head to head contest. In this study, we focus specifically on assembly factors that influence performance of short-duration contests in mid-sized teams playing a multiplayer online game, Dota2, where two teams consisting of five players each compete with each other. We determine the attributes and relational factors that help a team to defeat the opponent. Among attributes we consider the players’ skills as well as the diversity of their skills and their roles. Relational factors include the friendship relations within a team, previous co-playing experiences of team members as well as the embeddedness of the team, i.e., whether team members belong to a community that often plays together. We use game log data for short matches (under 30 minutes) within Dota2 to empirically test this model. We find that teams with players who have more diverse roles are more likely to win. We also find some evidence that teams consisting of players who have focused on training their fighting skills rather than on non-fighting skills have an advantage. However, when relational factors are included in the model, some skill factors are no longer significant. Instead, friendship ties between team members as well as the embeddedness of the team within the community have a positive impact on the likelihood of a team to win.
Huang, Yun; Neidhardt, Julia; Contractor, Noshir
Why Players Leave: Exploring Major Factors of Quitting EverQuest II Miscellaneous
2014.
@misc{ 20.500.12708_86040,
title = {Why Players Leave: Exploring Major Factors of Quitting EverQuest II},
author = {Yun Huang and Julia Neidhardt and Noshir Contractor},
year = {2014},
date = {2014-01-01},
abstract = {In online games as well as many online social sites, the success and attractiveness of a community is strongly determined by the active participation of its members. Analyzing why people leave and predicting churn behavior becomes a critical challenge, especially with the mutual influence among users. The purpose of this paper is to explore important factors that influence quitting decisions in games from three dimensions: achievement, commitment, and social network effects. In EverQuest II, a massively multiplayer online role-playing game, we identify different player attributes such as their progress and rewards in game, time committed on different game activities, and team and organization relations and examine their impacts on the likelihood of unsubscribing the game. In particular, we focus on social influence in players' teaming network and characterize the contagious effect of quitting behavior. We use a generalization of Exponential Random Graph Models (ERGM/p*) to study the social influence among users who played together. Our results show that players with higher achievement, such as higher levels, more award items, and more kills, are less likely to quit the game. The commitment on game activities has a mixed effect: players spend more time on building items are more likely to quit but players spend more time on trading items are less likely to quit. For social effects, we find that players who have more teammates and join a guild are less likely to quit. However, the likelihood of quitting increases significantly with the number of quitting teammates.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
In online games as well as many online social sites, the success and attractiveness of a community is strongly determined by the active participation of its members. Analyzing why people leave and predicting churn behavior becomes a critical challenge, especially with the mutual influence among users. The purpose of this paper is to explore important factors that influence quitting decisions in games from three dimensions: achievement, commitment, and social network effects. In EverQuest II, a massively multiplayer online role-playing game, we identify different player attributes such as their progress and rewards in game, time committed on different game activities, and team and organization relations and examine their impacts on the likelihood of unsubscribing the game. In particular, we focus on social influence in players’ teaming network and characterize the contagious effect of quitting behavior. We use a generalization of Exponential Random Graph Models (ERGM/p*) to study the social influence among users who played together. Our results show that players with higher achievement, such as higher levels, more award items, and more kills, are less likely to quit the game. The commitment on game activities has a mixed effect: players spend more time on building items are more likely to quit but players spend more time on trading items are less likely to quit. For social effects, we find that players who have more teammates and join a guild are less likely to quit. However, the likelihood of quitting increases significantly with the number of quitting teammates.
Neidhardt, Julia
A picture-based approach for travel recommendations Miscellaneous
2014.
@misc{ 20.500.12708_85978,
title = {A picture-based approach for travel recommendations},
author = {Julia Neidhardt},
year = {2014},
date = {2014-01-01},
abstract = {Personalized recommendation strongly relies on an accurate model to capture user preferences; eliciting this information is, in general, a hard problem. In the field of tourism this initial profiling becomes even more challenging. It has been shown that particularly in the beginning of the travel decision making process, users themselves are often not conscious of their needs and are not able to express them. Aiming at revealing implicitly given user preferences, this work introduces an approach that utilizes a set of travel related pictures to discover users' travel behavior and in turn, to deliver recommendations. Users first select three to seven pictures they like when thinking about their future travels. Then the selected pictures are mapped onto seven preference factors that reflect different travel behavioral aspects. The scores of the factors are used to recommend touristic point of interests. The pilot study shows that users are more motivated and satisfied using this non-verbal way of interaction. This talk discusses a stream of studies to quantify intangible user preferences and provide an easy and playful method to generate inputs/data for recommendation systems.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Personalized recommendation strongly relies on an accurate model to capture user preferences; eliciting this information is, in general, a hard problem. In the field of tourism this initial profiling becomes even more challenging. It has been shown that particularly in the beginning of the travel decision making process, users themselves are often not conscious of their needs and are not able to express them. Aiming at revealing implicitly given user preferences, this work introduces an approach that utilizes a set of travel related pictures to discover users’ travel behavior and in turn, to deliver recommendations. Users first select three to seven pictures they like when thinking about their future travels. Then the selected pictures are mapped onto seven preference factors that reflect different travel behavioral aspects. The scores of the factors are used to recommend touristic point of interests. The pilot study shows that users are more motivated and satisfied using this non-verbal way of interaction. This talk discusses a stream of studies to quantify intangible user preferences and provide an easy and playful method to generate inputs/data for recommendation systems.
Neidhardt, Julia; Schuster, Rainer; Seyfang, Leonhard; Werthner, Hannes
Eliciting the users’ unknown preferences Proceedings Article
In: Proceedings of the 8th ACM Conference on Recommender systems – RecSys ’14, ACM, New York, NY, USA, 2014.
@inproceedings{ 20.500.12708_55147,
title = {Eliciting the users' unknown preferences},
author = {Julia Neidhardt and Rainer Schuster and Leonhard Seyfang and Hannes Werthner},
doi = {10.1145/2645710.2645767},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings of the 8th ACM Conference on Recommender systems - RecSys '14},
publisher = {ACM},
address = {New York, NY, USA},
abstract = {Personalized recommendation strongly relies on an accurate model to capture user preferences; eliciting this information is, in general, a hard problem. In the field of tourism this initial profiling becomes even more challenging. It has been shown that particularly in the beginning of the travel decision making process, users themselves are often not conscious of their needs and are not able to express them. In this paper, the basics of a picture-based approach are introduced that aims at revealing implicitly given user preferences. Based on a set of travel related pictures selected by a user, an individual travel profile is deduced. This is accomplished by mapping those pictures onto seven basic factors that reflect different travel behavioral aspects. Also tourism products can be represented by this seven factor model. Thus, this model constitutes the basis of our recommendation algorithm. First tests show that this non-verbal way of interaction is experienced as exiting and inspiring.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Personalized recommendation strongly relies on an accurate model to capture user preferences; eliciting this information is, in general, a hard problem. In the field of tourism this initial profiling becomes even more challenging. It has been shown that particularly in the beginning of the travel decision making process, users themselves are often not conscious of their needs and are not able to express them. In this paper, the basics of a picture-based approach are introduced that aims at revealing implicitly given user preferences. Based on a set of travel related pictures selected by a user, an individual travel profile is deduced. This is accomplished by mapping those pictures onto seven basic factors that reflect different travel behavioral aspects. Also tourism products can be represented by this seven factor model. Thus, this model constitutes the basis of our recommendation algorithm. First tests show that this non-verbal way of interaction is experienced as exiting and inspiring.
2013
Neidhardt, Julia
Social Influence Analysis in Online Travel Communities Miscellaneous
2013.
@misc{ 20.500.12708_84842,
title = {Social Influence Analysis in Online Travel Communities},
author = {Julia Neidhardt},
doi = {10.1007/978-3-642-36309-2},
year = {2013},
date = {2013-01-01},
abstract = {We propose a framework that integrates network analysis techniques as well as methods for social influence analysis of both static and dynamic networks. In the context of Web-based travel communities, this framework could lead to deeper insights on how members of such a community are influenced by others. First, we discuss the important role of the Web and of social media in today's tourism landscape. To understand Web-related phenomena a theoretical framework is needed that is able to capture those dynamics. Based on the state-of-the-art, we then introduce our conceptual and methodological approach. Expected results are on the one hand concrete statements about online travel communities and on the other hand a classification of methods related to network and social influence analysis.},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
We propose a framework that integrates network analysis techniques as well as methods for social influence analysis of both static and dynamic networks. In the context of Web-based travel communities, this framework could lead to deeper insights on how members of such a community are influenced by others. First, we discuss the important role of the Web and of social media in today’s tourism landscape. To understand Web-related phenomena a theoretical framework is needed that is able to capture those dynamics. Based on the state-of-the-art, we then introduce our conceptual and methodological approach. Expected results are on the one hand concrete statements about online travel communities and on the other hand a classification of methods related to network and social influence analysis.
Pobiedina, Nataliia; Neidhardt, Julia; Moreno, Maria Carmen Calatrava; Werthner, Hannes
Ranking Factors of Team Success Proceedings Article
In: WWW 2013 Companion, pp. 1185–1193, Companion Publication of the IW3C2 WWW 2013 Conference, 2013, ISBN: 978-1-4503-2038-2.
@inproceedings{ 20.500.12708_54595,
title = {Ranking Factors of Team Success},
author = {Nataliia Pobiedina and Julia Neidhardt and Maria Carmen Calatrava Moreno and Hannes Werthner},
isbn = {978-1-4503-2038-2},
year = {2013},
date = {2013-01-01},
booktitle = {WWW 2013 Companion},
pages = {1185–1193},
publisher = {Companion Publication of the IW3C2 WWW 2013 Conference},
abstract = {As an increasing number of human activities are moving to the Web, more and more teams are predominantly virtual. Therefore, formation and success of virtual teams is an important issue in a wide range of fields. In this paper we model social behavior patterns of team work using data from virtual communities. In particular, we use data about the Web community of the multiplayer online game Dota~2 to study cooperation within teams. By applying statistical analysis we investigate how and to which extent different factors of the team in the game, such as role distribution, experience, number of friends and national diversity, have an influence on the team's success. In order to complete the picture we also rank the factors according to their influence. The results of our study imply that cooperation within the team is better than competition.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
As an increasing number of human activities are moving to the Web, more and more teams are predominantly virtual. Therefore, formation and success of virtual teams is an important issue in a wide range of fields. In this paper we model social behavior patterns of team work using data from virtual communities. In particular, we use data about the Web community of the multiplayer online game Dota~2 to study cooperation within teams. By applying statistical analysis we investigate how and to which extent different factors of the team in the game, such as role distribution, experience, number of friends and national diversity, have an influence on the team’s success. In order to complete the picture we also rank the factors according to their influence. The results of our study imply that cooperation within the team is better than competition.
Pobiedina, Nataliia; Neidhardt, Julia; Moreno, Maria Carmen Calatrava; Grad-Gyenge, Laszlo; Werthner, Hannes
On Successful Team Formation: Statistical Analysis of a Multiplayer Online Game Proceedings Article
In: 2013 IEEE 15th Conference on Business Informatics, IEEE, 2013.
@inproceedings{ 20.500.12708_54639,
title = {On Successful Team Formation: Statistical Analysis of a Multiplayer Online Game},
author = {Nataliia Pobiedina and Julia Neidhardt and Maria Carmen Calatrava Moreno and Laszlo Grad-Gyenge and Hannes Werthner},
doi = {10.1109/cbi.2013.17},
year = {2013},
date = {2013-01-01},
booktitle = {2013 IEEE 15th Conference on Business Informatics},
publisher = {IEEE},
abstract = {Teamwork plays an important role in many areas of today´s society, such as business activities. Thus, the question of how to form an effective team is of increasing interest. In this
paper we use the team-oriented multiplayer online game Dota 2 to study cooperation within teams and the success of teams. Making use of game log data, we choose a statistical approach to identify factors that increase the chance of a team to win. The factors
that we analyze are related to the roles that players can take within the game, the experiences of the players and friendship ties within a team. Our results show that such data can be used
to infer social behavior patterns.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Teamwork plays an important role in many areas of today´s society, such as business activities. Thus, the question of how to form an effective team is of increasing interest. In this
paper we use the team-oriented multiplayer online game Dota 2 to study cooperation within teams and the success of teams. Making use of game log data, we choose a statistical approach to identify factors that increase the chance of a team to win. The factors
that we analyze are related to the roles that players can take within the game, the experiences of the players and friendship ties within a team. Our results show that such data can be used
to infer social behavior patterns.
paper we use the team-oriented multiplayer online game Dota 2 to study cooperation within teams and the success of teams. Making use of game log data, we choose a statistical approach to identify factors that increase the chance of a team to win. The factors
that we analyze are related to the roles that players can take within the game, the experiences of the players and friendship ties within a team. Our results show that such data can be used
to infer social behavior patterns.
Neidhardt, Julia
Social Influence Analysis Networks and Teams Technical Report
2013.
@techreport{ 20.500.12708_38664,
title = {Social Influence Analysis Networks and Teams},
author = {Julia Neidhardt},
year = {2013},
date = {2013-01-01},
abstract = {This report summarizes the research conducted during my time as a visiting scholar at the SONIC lab at Northwestern University, i.e., from August 2013 until November 2013. The work was done in close cooperation with Yun Huang and Prof. Noshir Contractor from SONIC lab. The research stay was funded by the Austrian Marshall Plan Foundation.},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
This report summarizes the research conducted during my time as a visiting scholar at the SONIC lab at Northwestern University, i.e., from August 2013 until November 2013. The work was done in close cooperation with Yun Huang and Prof. Noshir Contractor from SONIC lab. The research stay was funded by the Austrian Marshall Plan Foundation.
2012
Fensel, Anna; Neidhardt, Julia; Pobiedina, Nataliia; Fensel, Dieter; Werthner, Hannes
Towards an Intelligent Framework to Understand and Feed the Web Proceedings Article
In: Abramowicz, Witold; Domingue, John; Węcel, Krzysztof (Ed.): Business Information Systems Workshops, pp. 255–266, Springer, Berlin, Heidelberg, 2012, ISBN: 9783642342271.
@inproceedings{ 20.500.12708_54208,
title = {Towards an Intelligent Framework to Understand and Feed the Web},
author = {Anna Fensel and Julia Neidhardt and Nataliia Pobiedina and Dieter Fensel and Hannes Werthner},
editor = {Witold Abramowicz and John Domingue and Krzysztof Węcel},
doi = {10.1007/978-3-642-34228-8_24},
isbn = {9783642342271},
year = {2012},
date = {2012-01-01},
booktitle = {Business Information Systems Workshops},
pages = {255–266},
publisher = {Springer},
address = {Berlin, Heidelberg},
abstract = {The Web is becoming a mirror of the "real" physical world. More and more aspects of our life move to the Web, thus also transforming this world. And the diversity of ways to communicate over the Internet has enormously grown. In this context communicating the right thing at the right time in the right way to the right person has become a remarkable challenge. In this conceptual paper we propose a framework to apply semantic technologies in combination with statistical and learning methods on Web and social media data to build a decision support framework. This framework should help professionals as well as normal users to optimize the spread of their information and the potential impact of this information on the Web.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The Web is becoming a mirror of the “real” physical world. More and more aspects of our life move to the Web, thus also transforming this world. And the diversity of ways to communicate over the Internet has enormously grown. In this context communicating the right thing at the right time in the right way to the right person has become a remarkable challenge. In this conceptual paper we propose a framework to apply semantic technologies in combination with statistical and learning methods on Web and social media data to build a decision support framework. This framework should help professionals as well as normal users to optimize the spread of their information and the potential impact of this information on the Web.
Piazzi, Roland; Baggio, Rodolfo; Neidhardt, Julia; Werthner, Hannes
Network Analysis of the Austrian eTourism Web Proceedings Article
In: Proceedings of ENTER Conference 2012, pp. 356–367, Springer Wien New York, 2012, ISBN: 978-3-7091-1141-3.
@inproceedings{ 20.500.12708_53860,
title = {Network Analysis of the Austrian eTourism Web},
author = {Roland Piazzi and Rodolfo Baggio and Julia Neidhardt and Hannes Werthner},
isbn = {978-3-7091-1141-3},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of ENTER Conference 2012},
pages = {356–367},
publisher = {Springer Wien New York},
abstract = {Network analysis methods have gained much attention in the last years and have provided a wealth of insights into the structural and dynamic properties of many systems. Here these methods are applied to the study of a destination´s tourism webspace. This exploratory analysis aims at showing how these techniques can be used and what outcomes can be obtained. After a short introduction to network analysis and a brief review of the literature, the network analysis of the Austrian eTourism Web is described in detail. The data collection methods are explained and the characteristic network parameters are calculated. Then the results are discussed and interpreted.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Network analysis methods have gained much attention in the last years and have provided a wealth of insights into the structural and dynamic properties of many systems. Here these methods are applied to the study of a destination´s tourism webspace. This exploratory analysis aims at showing how these techniques can be used and what outcomes can be obtained. After a short introduction to network analysis and a brief review of the literature, the network analysis of the Austrian eTourism Web is described in detail. The data collection methods are explained and the characteristic network parameters are calculated. Then the results are discussed and interpreted.
2011
Piazzi, Roland; Baggio, Rodolfo; Neidhardt, Julia; Werthner, Hannes
Destinations and the Web: a Network Analysis View Journal Article
In: Information Technology and Tourism, vol. 13, iss. 3, pp. 215–228, 2011, ISSN: 1098-3058.
@article{ 20.500.12708_162802,
title = {Destinations and the Web: a Network Analysis View},
author = {Roland Piazzi and Rodolfo Baggio and Julia Neidhardt and Hannes Werthner},
doi = {10.3727/109830512x13283928066913},
issn = {1098-3058},
year = {2011},
date = {2011-01-01},
journal = {Information Technology and Tourism},
volume = {13},
issue = {3},
pages = {215–228},
abstract = {Network analysis methods have gained much attention in the last years and have provided a wealth of insights into the structural and dynamic properties of many systems. Here we apply these methods to the study of tourism destinations' webspaces. This exploratory analysis aims at showing how these techniques can be used and what outcomes can be obtained. After a short introduction to network analysis and a brief review of the literature, two cases are presented, namely Austria as a whole country and a smaller destination within Italy: the island of Elba. For each case, data collection methods are described and the characteristic network parameters are calculated. The comparison between the two cases highlights both similarities and differences, which are described and interpreted. Finally, the limitations of this approach are discussed.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Network analysis methods have gained much attention in the last years and have provided a wealth of insights into the structural and dynamic properties of many systems. Here we apply these methods to the study of tourism destinations’ webspaces. This exploratory analysis aims at showing how these techniques can be used and what outcomes can be obtained. After a short introduction to network analysis and a brief review of the literature, two cases are presented, namely Austria as a whole country and a smaller destination within Italy: the island of Elba. For each case, data collection methods are described and the characteristic network parameters are calculated. The comparison between the two cases highlights both similarities and differences, which are described and interpreted. Finally, the limitations of this approach are discussed.