ABSTRACT: Recommendation and ranking systems are known to suffer from popularity bias; the tendency of the algorithm to favor a few popular items while under-representing the majority of other items. Prior research has examined various approaches for mitigating popularity bias and enhancing the recommendation of long-tail, less popular, items. The effectiveness of these approaches is often assessed using different metrics to evaluate the extent to which over-concentration on popular items is reduced. However, not much attention has been given to the user-centered evaluation of this bias; how different users with different levels of interest towards popular items (e.g., niche vs blockbuster-focused users) are affected by such algorithms. In this talk, I first give an overview of the popularity bias problem in recommender systems. Then, I show the limitations of the existing metrics to evaluate popularity bias mitigation when we want to assess these algorithms from the users’ perspective and I propose a new metric that can address these limitations. In addition, I present an effective approach that mitigates popularity bias from the user-centered point of view. Finally, I investigate several state-of-the-art approaches proposed in recent years to mitigate popularity bias and evaluate their performances using the existing metrics and also from the users’ perspective. Using two publicly available datasets, I show that many of the existing popularity bias mitigation techniques ignore the users' tolerance towards popular items. The proposed user-centered method, on the other hand, can tackle popularity bias effectively for different users while also improving the existing metrics.

ABSTRACT: Recommender systems are systems that help users in decision-making situations where there is an abundance of choices. We can find them in our everyday lives, for example in online shops. State-of-the-art research in recommender systems has shown the benefits of behavioural modeling. Behavioural modeling means that we use past ratings, purchases, clicks etc. to model the user preferences. However, behavioural modeling is not able to capture certain aspects of the user preferences. In this talk I will show how the usage of complementary research in computational psychology, such as detection of personality and emotions, can benefit recommender systems.