CIIR Talk Series: Zhaochun Ren, Towards Empathetic Conversational Recommender Systems

Content

Image

Speaker 

Zhaochun Ren, Leiden University, The Netherlands 

Abstract

Conversational Recommender Systems (CRS) enable dynamic, interactive dialogues between users and recommender systems, capturing preferences through iterative exchanges. However, many existing approaches fall short due to limited contextual understanding and insufficient attention to the emotional and empathetic dimensions of user interactions. In contrast, empathetic dialogue systems excel at recognizing user emotions and generating emotionally resonant responses for deeper user engagement. This talk will present our recent efforts to bridge these gaps through an empathetic conversational recommendation framework by combining insights from our studies about knowledge-enhanced CRS and empathetic dialogue systems. By integrating insights from knowledge-enhanced CRS and empathetic dialogue systems, our framework incorporates external knowledge, advanced dialogue generation techniques, and emotional awareness to refine user preference modeling and optimize conversational responses. We tackle critical challenges, including insufficient supervision, limited contextual understanding, incomplete external knowledge, and emotionally detached interactions, proposing solutions to improve both recommendation accuracy and user satisfaction. Additionally, I will introduce how the synergy of multiple large language model agents enables CRS systems to improve user satisfaction and interaction quality. The talk will conclude with an exploration of the remaining challenges and future directions for CRS.

Bio

Dr. Zhaochun Ren is an Associate Professor at Leiden University, the Netherlands. He is interested in information retrieval and natural language processing, with an emphasis on conversational artificial intelligence, recommender systems, and information retrieval. He aims to develop intelligent agents that can address complex user requests and solve core challenges in NLP and IR towards that goal. His research has been recognized with multiple awards at RecSys, SIGIR, WSDM, EMNLP, and CIKM. Prior to joining Leiden, he was a Professor at Shandong University and a Research Scientist at JD.com.

Subscribe to mailing list by sending an email to ciir-talks-request [at] cs [dot] umass [dot] edu (ciir-talks-request[at]cs[dot]umass[dot]edu) with "subscribe" as the email subject (without the quotation marks) for Zoom link/passcode notifications, or click here for Zoom link and reach out to zamani [at] cs [dot] umass [dot] edu (subject: CIIR%20Talks%20Passcode) (Hamed Zamani) for the passcode.