Mitigation of Popularity Bias in Recommendation Systems

In response to the quantity of information available on the Internet, many online service providers are attempting to customize their services and make content access more simple via recommender systems (RSs) to support users in discovering the products they are most likely interested in. However, these recommendation systems are prone to popularity bias, which is a tendency to promote popular items even if they do not satisfy a user’s preferences and then provide customers with recommendations of poor quality. Such a bias has a negative influence on both users and item providers. It is then essential to mitigate such bias in order to guarantee that less popular but pertinent items show up on the user’s recommendation list. In this work, we conduct an empirical analysis of different mitigation techniques for popularity bias to provide an overview of the present state of the art of popularity bias and raise the fairness issue in RSs