Towards Fair Conversational Recommender Systems

TL;DR

This paper highlights the importance of addressing bias in conversational recommender systems and proposes key questions to guide future research towards fairness in these interactive systems.

Contribution

It introduces a focus on bias mitigation in conversational recommenders and outlines fundamental questions for advancing fairness in this emerging area.

Findings

Bias affects conversational recommender systems.

Identifies key questions for fairness research.

Calls for dedicated methods to counteract bias.

Abstract

Conversational recommender systems have demonstrated great success. They can accurately capture a user's current detailed preference -- through a multi-round interaction cycle -- to effectively guide users to a more personalized recommendation. Alas, conversational recommender systems can be plagued by the adverse effects of bias, much like traditional recommenders. In this work, we argue for increased attention on the presence of and methods for counteracting bias in these emerging systems. As a starting point, we propose three fundamental questions that should be deeply examined to enable fairness in conversational recommender systems.