Simulations for novel problems in recommendation: analyzing misinformation and data characteristics

Abstract

In this position paper, we discuss recent applications of simulation approaches for recommender systems tasks. In particular, we describe how they were used to analyze the problem of misinformation spreading and understand which data characteristics affect the performance of recommendation algorithms more significantly. We also present potential lines of future work where simulation methods could advance the work in the recommendation community.

References in corpus (5)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Analyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?
• Analysing the Effect of Recommendation Algorithms on the Amplification of Misinformation
• Partially Synthetic Data for Recommender Systems: Prediction Performance and Preference Hiding
• T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems