Diversity in News Recommendations- Towards a Broader Perspective on Diversity-Aware-Recommender-Systems and Their Influence on Users

Author: Linda Basso

Supervisor: Irina Nalis-Neuner, Co-Supervisor: Julia Neidhardt


All of us encounter recommender systems (RS) regularly by using social media, google, online-shopping, streaming music, reading the news online, etc. The interaction with these information filtering systems is part of our everyday lives. Thus, they have an influence on their users’ behavior, their decision making and opinion forming. Considering this, the question arises, whether these systems must take certain responsibilities and implement basic human values, which are important to sustain and advance the democratic society we live in. The demand of socially responsible designs for news recommender systems is currently of the utmost relevance. In this paper, the focus lies on news recommender systems (NRS) and the request for diversified content to ensure the democratic value of diversity and examine the influence on the users as individuals. Therefore, an online experimental study was conducted to examine the positive influence of diverse news recommendations on users’ subjective wellbeing. The participants were split into two groups, each of them interacted with one NRS, the experimental group with a diverse NRS, the control group with a non-diversified NRS. Then, the subjective wellbeing and the personal evaluation of the RS was measured. It was found, that while most of the participants agreed to the importance of diversity in the media, the subjective wellbeing did not significantly differ within the two groups after interacting with one of the two NRS. Thus, participants’ subjective wellbeing was not positively affected after consuming more diverse news.