PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 5457–5467 August 1–6, 2021. ©2021 Association for Computational Linguistics 5457 PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity Tao Qi1, Fangzhao Wu2, Chuhan Wu1 and Yongfeng Huang1 1Department of Electronic Engineering & BNRist, Tsinghua University, Beijing 100084, China 2Microsoft Research Asia, Beijing 100080, China {taoqi.qt, wufangzhao, wuchuhan15}@gmail.com yfhuang@mail.tsinghua.edu.cn Abstract Personalized news recommendation methods are widely used in online news services. These methods usually recommend news based on the matching between news content and user interest inferred from historical behaviors. However, these methods usually have difficul- ties in making accurate recommendations to cold-start users, and tend to recommend sim- ilar news with those users have read. In gen- eral, popular news usually contain important information and can attract users with differ- ent interests. Besides, they are usually diverse in content and topic. Thus, in this paper we propose to incorporate news popularity infor- mation to alleviate the cold-start and diversity problems for personalized news recommenda- tion. In our method, the ranking score for rec- ommending a candidate news to a target user is the combination of a personalized matching score and a news popularity score. The former is used to capture the personalized user inter- est in news. The latter is used to measure time- aware popularity of candidate news, which is predicted based on news content, recency, and real-time CTR using a unified framework. Be- sides, we propose a popularity-aware user en- coder to eliminate the popularity bias in user behaviors for accurate interest modeling. Ex- periments on two real-world datasets show our method can effectively improve the accuracy and diversity for news recommendation. 1 Introduction Personalized news recommendation is a useful tech- nique to help users alleviate information overload when visiting online news platforms (Wu et al., 2020d,b, 2021; Ge et al., 2020). Existing personal- ized news recommendation methods usually recom- mend news to a target user based on the matching between the content of candidate news and user in- terest inferred from previous behaviors (Zhu et al., 2019; Wu et al., 2019f). For example, Wu et al. 6.1 magnitude quake rattles Alaska Biden aims to rebuild and expand legal immigration Returning to normal is not simple for everyone Man accused of plotting Walmart attack arrested Russia diplomat warns US ahead of summit Black Wall Street was shattered 100 years ago Figure 1: Several example popular news. (2019e) proposed to model news content from news title based on multi-head self-attention. In addi- tion, they modeled user interest from the previously clicked news articles with multi-head self-attention to capture the relatedness between different behav- iors. An et al. (2019) proposed to use CNN network to learn news embeddings from news titles and cat- egories, and model both long-term and short-term user interests from news click behaviors. However, these personalized news recommendation methods usually have difficulties in making accurate recom- mendations to cold-start users, since …

Content truncated to 500 words