IP2: Entity-Guided Interest Probing for Personalized News Recommendation

2025-07-17

AI Summary

Existing news recommendation systems overlook the critical role of entities in user interest modeling, failing to distinguish and model users’ heterogeneous interests in intra-news entities (e.g., persons, locations) versus inter-news co-occurring entities. To address this, we propose IP2—a novel framework that *first* decouples entity-level interest into intra-news and inter-news hierarchical dimensions, explicitly aligning with users’ three-stage reading behavior: browsing, clicking, and in-depth reading. Methodologically, IP2 introduces a Transformer-based entity encoder, signature-guided entity–title contrastive pretraining, a dual-tower user encoder, and cross-tower attention to enable fine-grained interest detection and behavioral alignment. Extensive experiments on two real-world datasets demonstrate that IP2 significantly outperforms state-of-the-art methods, validating the effectiveness of hierarchical entity interest modeling for news recommendation.

Technology Category

• Natural Language Processing: Information Extraction
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Content-based information diffusion
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

News recommender systems aim to provide personalized news reading experiences for users based on their reading history. Behavioral science studies suggest that screen-based news reading contains three successive steps: scanning, title reading, and then clicking. Adhering to these steps, we find that intra-news entity interest dominates the scanning stage, while the inter-news entity interest guides title reading and influences click decisions. Unfortunately, current methods overlook the unique utility of entities in news recommendation. To this end, we propose a novel method called IP2 to probe entity-guided reading interest at both intra- and inter-news levels. At the intra-news level, a Transformer-based entity encoder is devised to aggregate mentioned entities in the news title into one signature entity. Then, a signature entity-title contrastive pre-training is adopted to initialize entities with proper meanings using the news story context, which in the meantime facilitates us to probe for intra-news entity interest. As for the inter-news level, a dual tower user encoder is presented to capture inter-news reading interest from both the title meaning and entity sides. In addition to highlighting the contribution of inter-news entity guidance, a cross-tower attention link is adopted to calibrate title reading interest using inter-news entity interest, thus further aligning with real-world behavior. Extensive experiments on two real-world datasets demonstrate that our IP2 achieves state-of-the-art performance in news recommendation.

Problem

• Modeling entity-guided interest in news recommendation
• Capturing intra-news and inter-news entity interactions
• Aligning recommendation with real-world reading behavior

Innovation

• Transformer-based entity encoder aggregates title entities
• Signature entity-title contrastive pre-training initializes entities
• Dual tower user encoder captures inter-news interest