Item Popularity
Item popularity, a key factor in recommendation systems and other ranking-based applications, focuses on understanding and predicting the relative success of different items. Current research emphasizes mitigating popularity bias, which skews recommendations towards already-popular items, often using techniques like large language models (LLMs) to incorporate richer item and user information, and employing advanced algorithms such as matrix factorization and graph-based methods to capture complex relationships between items and users. Addressing this bias and improving the representation of less popular items is crucial for enhancing user experience, promoting diversity, and ensuring fairness in recommendation systems and other applications that rely on item ranking.
Papers
Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias
Miaomiao Cai, Lei Chen, Yifan Wang, Haoyue Bai, Peijie Sun, Le Wu, Min Zhang, Meng Wang
LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation
Qidong Liu, Xian Wu, Yejing Wang, Zijian Zhang, Feng Tian, Yefeng Zheng, Xiangyu Zhao