Modeling Behavioral Patterns in News Recommendations Using Fuzzy Neural Networks

2026-01-07

arXiv.org

AI Summary

This work proposes a novel approach to news recommendation by introducing fuzzy neural networks to address the limited interpretability of prevailing black-box models, which often fail to provide actionable insights for editorial decision-making. The method automatically learns human-readable rules from user behavior data to predict click-through behavior, while enabling a flexible trade-off between rule complexity and interpretability through a configurable threshold. Evaluated on the MIND and EB-NeRD datasets, the proposed model outperforms multiple baseline approaches in click prediction accuracy. Moreover, it generates interpretable rules with practical curation value, uncovering underlying patterns in user news consumption and facilitating better alignment between content editing strategies and audience behavior.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

News recommender systems are increasingly driven by black-box models, offering little transparency for editorial decision-making. In this work, we introduce a transparent recommender system that uses fuzzy neural networks to learn human-readable rules from behavioral data for predicting article clicks. By extracting the rules at configurable thresholds, we can control rule complexity and thus, the level of interpretability. We evaluate our approach on two publicly available news datasets (i.e., MIND and EB-NeRD) and show that we can accurately predict click behavior compared to several established baselines, while learning human-readable rules. Furthermore, we show that the learned rules reveal news consumption patterns, enabling editors to align content curation goals with target audience behavior.

Problem

• news recommender systems
• interpretability
• behavioral patterns
• click prediction
• transparent models

Innovation

• fuzzy neural networks
• interpretable recommendation
• human-readable rules
• news recommender systems
• behavioral pattern modeling