User Interest
User interest modeling aims to understand and predict individual preferences to personalize experiences, primarily in recommendation systems and related applications. Current research focuses on representing user interests in multimodal spaces, leveraging large language models to explore novel interests, and dynamically adapting interest representations to different contexts using techniques like attention mechanisms and hierarchical frameworks. These advancements significantly improve the accuracy and relevance of personalized recommendations, impacting user engagement across various online platforms and potentially informing other areas like personalized healthcare and education.
Papers
Producing Usable Taxonomies Cheaply and Rapidly at Pinterest Using Discovered Dynamic $\mu$-Topics
Abhijit Mahabal, Jiyun Luo, Rui Huang, Michael Ellsworth, Rui Li
Decision-Making Context Interaction Network for Click-Through Rate Prediction
Xiang Li, Shuwei Chen, Jian Dong, Jin Zhang, Yongkang Wang, Xingxing Wang, Dong Wang
Aligning Recommendation and Conversation via Dual Imitation
Jinfeng Zhou, Bo Wang, Minlie Huang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
Forecasting User Interests Through Topic Tag Predictions in Online Health Communities
Amogh Subbakrishna Adishesha, Lily Jakielaszek, Fariha Azhar, Peixuan Zhang, Vasant Honavar, Fenglong Ma, Chandra Belani, Prasenjit Mitra, Sharon Xiaolei Huang