Host: The Japanese Society for Artificial Intelligence
Name : The 36th Annual Conference of the Japanese Society for Artificial Intelligence
Number : 36
Location : [in Japanese]
Date : June 14, 2022 - June 17, 2022
The diversity of recommender systems is well analyzed, but the impact of their diversity on user engagement is less understood. Our study reveals the relationship between diversity and engagement in the news domain and introduces the impact of popularity bias per user as a metric of diversity. In this study, we introduce the notion of popularity diversity, propose metrics for it, and analyze user behavior on popular news applications in terms of content diversity and popularity diversity, the impact of which we find to be closely related to user activity. We also find that users who view more articles in these services tend to higher content diversity and popularity diversity, and that the diversity metrics improves the prediction accuracy of users' service withdrawal. Furthermore, we confirmed that there is a moderate positive correlation between the diversity of displayed articles and the diversity of clicked articles, indicating that the diversity of clicked articles is influenced by the diversity of displayed articles, but that the diversity of displayed articles alone is insufficient to explain user behavior.
