A Look Into News Avoidance Through AWRS: An Avoidance-Aware Recommender System

2024-07-12

arXiv.org

AI Summary

Existing news recommendation systems inadequately model user avoidance behavior—where users deliberately skip or ignore recommended items—despite its strong signal of explicit negative preference. Method: This paper proposes the first recommendation framework that treats avoidance as an explicit negative feedback signal, introducing a novel “exposure–relevance–avoidance” tri-dimensional collaborative modeling paradigm. We design an avoidance-aware multi-task learning architecture with a dynamic weighting mechanism, enabling unified multilingual modeling and personalization across English, Norwegian, and Japanese news. Contribution/Results: Extensive experiments on three multilingual news datasets demonstrate consistent and significant improvements over state-of-the-art baselines across key metrics—including click-through rate (CTR), normalized discounted cumulative gain (NDCG), and long-term user retention—validating that explicit avoidance modeling critically enhances both recommendation accuracy and sustainable user engagement.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In recent years, journalists have expressed concerns about the increasing trend of news article avoidance, especially within specific domains. This issue has been exacerbated by the rise of recommender systems. Our research indicates that recommender systems should consider avoidance as a fundamental factor. We argue that news articles can be characterized by three principal elements: exposure, relevance, and avoidance, all of which are closely interconnected. To address these challenges, we introduce AWRS, an Avoidance-Aware Recommender System. This framework incorporates avoidance awareness when recommending news, based on the premise that news article avoidance conveys significant information about user preferences. Evaluation results on three news datasets in different languages (English, Norwegian, and Japanese) demonstrate that our method outperforms existing approaches.

Problem

• Recommendation System
• News Avoidance
• User Satisfaction

Innovation

• AWRS
• User Information Avoidance
• Multilingual News Recommendation