Wednesday, 23 June 2021 Marko Tkalčič, PhD published the paper in the prestigious journal Elsevier Information Processing and Management
Assoc. prof. Marko Tkalčič, PhD has recently published the paper "Investigating the impact of recommender systems on user-based and item-based popularity bias" in the prestigious journal Elsevier Information Processing and Management (impact factor = 4.787, A") in co-authorship with partners from the University of Bergen, Norway and the University of Oulu, Finland.
The paper investigates how recommendation algorithms influence the popularity bias on the Twitter platform. The results indicate that in certain cases the bias is reinforced by the recommendation algorithm and in other cases it is decreased. There are important implications in designing artificial intelligence algorithms that are fair, i.e. they do not induce bias, which is one of the main concerns in modern AI research
You can access the paper is at this link.