IP2: Entity-Guided Interest Probing for Personalized News Recommendation

TL;DR

This paper introduces IP2, a novel news recommendation method that leverages entity-guided interest probing at intra- and inter-news levels, significantly improving personalization by modeling user reading behavior more accurately.

Contribution

IP2 is the first approach to explicitly incorporate entity-guided interest probing at both intra- and inter-news levels in news recommendation systems.

Findings

IP2 achieves state-of-the-art performance on real-world datasets.

The Transformer-based entity encoder effectively captures entity significance.

Cross-tower attention calibration improves interest modeling accuracy.

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.