Modeling Stage-wise Evolution of User Interests for News Recommendation

ArXi:2603.10471v1 Announce Type: cross Personalized news recommendation is highly time-sensitive, as user interests are often driven by emerging events, trending topics, and shifting real-world contexts. These dynamics make it essential to model not only users' long-term preferences, which reflect stable reading habits and high-order collaborative patterns, but also their short-term, context-dependent interests that change rapidly over time.