News Recommendation Method Based on Candidate-Aware Long- and Short-Term Preference Modeling

Personalized news recommendations focus on providing users with news that fits their interests and alleviates their information overload. User preference modeling is crucial for achieving personalized news recommendations, and user preferences are usually expressed as long-term and short-term user preferences. Existing news recommendation methods have difficulty accurately matching user preferences with candidate news, which is the main challenge plaguing the news recommendation field. For this purpose, we propose a novel news recommendation method based on candidate-aware long- and short-term preference modeling, named NRCLS. The method contains: (1) a Candidate-Enhanced graph attention network, which learns high-order structural information in graphs, mines the potential relationship between long-term user preferences and candidate news; and (2) a candidate-aware attention network that incorporates news subtopics. In this network, the dynamic impact of candidate news on short-term user preferences is considered. Results on real-world datasets demonstrate the effectiveness of our proposed method in improving the performance of news recommendations. We have also conducted several ablation studies that demonstrate the effectiveness of the core module in NRCLS.