Is This News Still Interesting to You?: Lifetime-aware Interest Matching for News Recommendation

2025-08-18

AI Summary

Personalized news recommendation faces two time-sensitive challenges: (1) insufficient modeling of user interest decay over click latency, and (2) neglect of the dynamic heterogeneity in news item lifetimes—varying across topics and users. To address these, we propose the Lifetime-aware Interest Matching Framework (LIME), the first method to jointly model click age and cross-topic/user news lifetime differences. LIME introduces three key components: (i) user- and topic-aware age representations; (ii) candidate-aware lifetime attention; and (iii) freshness-guided interest refinement. By incorporating time-aligned dynamic attention and prediction-time interest optimization, LIME enables fine-grained characterization of both interest decay and news timeliness. Compatible with mainstream backbone models, LIME achieves significant improvements over state-of-the-art methods on two real-world datasets, demonstrating its effectiveness and generalizability in time-sensitive recommendation scenarios.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Life-Long and Continual Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Content-based information diffusion
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Personalized news recommendation aims to deliver news articles aligned with users' interests, serving as a key solution to alleviate the problem of information overload on online news platforms. While prior work has improved interest matching through refined representations of news and users, the following time-related challenges remain underexplored: (C1) leveraging the age of clicked news to infer users' interest persistence, and (C2) modeling the varying lifetime of news across topics and users. To jointly address these challenges, we propose a novel Lifetime-aware Interest Matching framework for nEws recommendation, named LIME, which incorporates three key strategies: (1) User-Topic lifetime-aware age representation to capture the relative age of news with respect to a user-topic pair, (2) Candidate-aware lifetime attention for generating temporally aligned user representation, and (3) Freshness-guided interest refinement for prioritizing valid candidate news at prediction time. Extensive experiments on two real-world datasets demonstrate that LIME consistently outperforms a wide range of state-of-the-art news recommendation methods, and its model agnostic strategies significantly improve recommendation accuracy.

Problem

• Infer user interest persistence using clicked news age
• Model varying news lifetime across topics and users
• Improve news recommendation with time-aware strategies

Innovation

• User-Topic lifetime-aware age representation
• Candidate-aware lifetime attention mechanism
• Freshness-guided interest refinement strategy