D-RDW: Diversity-Driven Random Walks for News Recommender Systems

2025-08-18

AI Summary

This paper addresses the dual challenges of insufficient diversity and opaque value alignment in news recommendation. To this end, we propose D-RDW, a lightweight algorithm that integrates traditional random walks with editable, attribute-specific target distributions—such as sentiment polarity or political orientation—to enable diversity-driven navigation and attribute-constrained re-ranking. Crucially, D-RDW achieves controllable and interpretable diversification without relying on complex neural architectures. Its core innovation lies in a modular, user-editable attribute distribution mechanism that transparently embeds societal values into the recommendation pipeline. Extensive experiments demonstrate that D-RDW outperforms state-of-the-art neural recommenders in diversity, fairness, and computational efficiency, achieving significantly faster inference times. Thus, D-RDW establishes a novel paradigm for value-sensitive news dissemination.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Recommender Systems
• Search and Optimization: Distributed Search

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

This paper introduces Diversity-Driven RandomWalks (D-RDW), a lightweight algorithm and re-ranking technique that generates diverse news recommendations. D-RDW is a societal recommender, which combines the diversification capabilities of the traditional random walk algorithms with customizable target distributions of news article properties. In doing so, our model provides a transparent approach for editors to incorporate norms and values into the recommendation process. D-RDW shows enhanced performance across key diversity metrics that consider the articles' sentiment and political party mentions when compared to state-of-the-art neural models. Furthermore, D-RDW proves to be more computationally efficient than existing approaches.

Problem

• Enhances diversity in news recommendations using random walks
• Incorporates editorial norms into transparent recommendation processes
• Improves computational efficiency over current neural models

Innovation

• Diversity-Driven RandomWalks for recommendations
• Combines random walks with customizable distributions
• Computationally efficient and transparent approach