Diversity Matters: User-Centric Multi-Interest Learning for Conversational Movie Recommendation

ACMMM 2024

Yongsen Zheng, Guohua Wang, Yang Liu, Liang Lin

ACMMM 2024

Abstract

Diversity plays a crucial role in Recommender Systems (RSs) as it ensures a wide range of recommended items, providing users with access to new and varied options. Without diversity, users often encounter repetitive content, limiting their exposure to novel choices. While significant efforts begin to enhance recommendation diversification in static offline scenarios, relatively less attention has been given to online Conversational Recommender Systems (CRSs). However, the lack of recommendation diversity in CRSs will increasingly exacerbate over time due to the dynamic user-system feedback loop, resulting in challenges such as the Matthew effect, filter bubbles, and echo chambers. To address these issues, we propose a novel paradigm, User-Centric Multi-Interest Learning for Conversational Movie Recommendation (CoMoRec), aiming to learn multiple user interests to improve result diversity for movie recommendations. Firstly, CoMoRec automatically models various facets of user interests, including context-, graph-, and review-based interests, to explore a wide range of user potential intentions. Then, it leverages these multi-aspect user interests to accurately predict personalized and diverse movie recommendations and generate fluent and informative responses during conversations. Extensive experiments on two publicly CRS-based movie datasets show that our CoMoRec achieves a new state-of-the-art performance and the superiority of improving recommendation diversity in the CRS.

Framework

Experiment

Conclusion

To improve recommendation diversification for movie predictions, we propose a novel paradigm, CoMoRec, comprising User-Centric Multi-Interest Learning and Interest-Enhanced CRS. The former aims to explore the wide array of user interests, including context-, graph-, and review-based interests, to enrich the result diversity for conversational movie recommendations, while the latter devotes to employ these multiple user interests to predict items and generate responses effectively. Extensive experiments on two publicly CRS-based movie datasets show that our CoMoRec achieves a new state-of-the-art performance, and the superior of improving recommendation diversification in the CRS.

Acknowledgement

This work was supported by National Science and Technology Major Project (No.2021ZD0111601), National Natural Science Foundation of China (No.62325605), and Guangdong Basic and Applied Basic Research Foundation (No.2023A1515011374, No.2023A1515011530), and Guangzhou Science and Technology Program (No.2024A04J6365, No. 2023A04J2030), and Guangzhou Basic Research Project for Basic and Applied Research (Project No. 202201010334), and Guangdong Province Key Laboratory of Information Security Technology, Sun Yat-sen University.

中山大学人机物智能融合实验室 Human Cyber Physical Intelligence Integration Lab

hcp@sysu.edu.cn
广州市广州大学城外环东路132号

Official Account

News: Achievements; Activities; sharings; Talks

People: Faculty; Students; Alumni

Projects: Computer Vision; Multimodal; Robotics

Links: Git-Lab