Don't Click the Bait: Title Debiasing News Recommendation via Cross-Field Contrastive Learning

TL;DR

This paper introduces TDNR-C2, a novel news recommendation method that uses cross-field contrastive learning to mitigate title bias by leveraging news abstracts, improving recommendation accuracy.

Contribution

The paper proposes a new framework that incorporates news abstracts and cross-field contrastive learning to effectively reduce title bias in news recommendation systems.

Findings

TDNR-C2 outperforms existing methods on real-world datasets.

News abstracts significantly enhance title debiasing.

Cross-field contrastive learning effectively aligns knowledge from different news fields.

Abstract

News recommendation emerges as a primary means for users to access content of interest from the vast amount of news. The title clickbait extensively exists in news domain and increases the difficulty for news recommendation to offer satisfactory services for users. Fortunately, we find that news abstract, as a critical field of news, aligns cohesively with the news authenticity. To this end, we propose a Title Debiasing News Recommendation with Cross-field Contrastive learning (TDNR-C2) to overcome the title bias by incorporating news abstract. Specifically, a multi-field knowledge extraction module is devised to extract multi-view knowledge about news from various fields. Afterwards, we present a cross-field contrastive learning module to conduct bias removal via contrasting learned knowledge from title and abstract fileds. Experimental results on a real-world dataset demonstrate the superiority of the proposed TDNR-C2 over existing state-of-the-art methods. Further analysis also indicates the significance of news abstract for title debiasing.