Causal Estimation for Conversational Recommender System

In this project, we study popularity bias in Recommender System (RecSys), Conversational Recsys, and their interplays.

Poster image to be added

Description

We discover (1) conversation can significantly mitigate popularity bias for traditional RecSys; (2) Conversation RecSys suffers from popularity bias itself. We propose a method to mitigate popularity bias in Conversational RecSys.

Please refer to our poster for technical details.

Our experiment is still WIP, we will update on this github repo: https://github.com/YisongMiao/cs6101