Balancing Domestic and Global Perspectives: Evaluating Dual-Calibration and LLM-Generated Nudges for Diverse News Recommendation

2026-03-06

AI Summary

This study addresses the imbalance between local and international news consumption and the lack of diversity in user reading behaviors within news recommendation systems. To mitigate these issues, the authors propose an integrated approach combining algorithmic intervention with large language models (LLMs). Specifically, they design a topic–region dual-calibration recommendation algorithm and leverage LLM-generated personalized presentation prompts to gently steer users toward more diverse domestic and international news content. A longitudinal field experiment conducted in a real-world user environment demonstrates that the proposed method significantly enhances both the diversity of news exposure and actual consumption. Furthermore, personalized relevance prompts outperform generic thematic recommendations, and sustained exposure to calibrated content effectively shapes users’ long-term reading preferences toward greater balance.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this study, we applied the ``personalized diversity nudge framework''with the goal of expanding user reading coverage in terms of news locality (i.e., domestic and world news). We designed a novel topic-locality dual calibration algorithmic nudge and a large language model-based news personalization presentation nudge, then launched a 5-week real-user study with 120 U.S. news readers on the news recommendation experiment platform POPROX. With user interaction logs and survey responses, we found that algorithmic nudges can successfully increase exposure and consumption diversity, while the impact of LLM-based presentation nudges varied. User-level topic interest is a strong predictor of user clicks, while highlighting the relevance of news articles to prior read articles outperforms generic topic-based and no personalization. We also demonstrate that longitudinal exposure to calibrated news may shift readers'reading habits to value a balanced news digest from both domestic and world articles. Our results provide direction for future work on nudging for diverse consumption in news recommendation systems.

Problem

• news recommendation
• personalized diversity
• locality balance
• user exposure diversity
• reading habit

Innovation

• dual-calibration
• LLM-generated nudges
• personalized diversity
• news recommendation
• reading habit shift