PolicyStory: Leveraging Large Language Models to Generate Comprehensible Summaries of Policy-News in India

2025-09-09

AI Summary

To address public difficulties in systematically comprehending India’s complex policy issues amid information overload, this paper proposes a policy news summarization framework integrating longitudinal media discourse analysis with open-source large language models (LLMs). Methodologically, it employs multi-source news crawling, dynamic topic clustering, timeline modeling, and prompt-engineered LLM-based summarization to generate multi-granular, temporally structured policy summaries. Its key contribution lies in the first systematic integration of temporal evolution modeling with LLMs to construct an interpretable, traceable narrative of policy development. User evaluation demonstrates that the framework significantly enhances long-term cognitive efficiency regarding policy dynamics; summary clarity and tool usability received strong endorsement. This work provides a scalable technical pathway for public policy communication and digital literacy interventions.

Technology Category

• Natural Language Processing: Summarization
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Data Visualization & Summarization

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

In the era of information overload, traditional news consumption through both online and print media often fails to provide a structured and longitudinal understanding of complex sociopolitical issues. To address this gap, we present PolicyStory, an information tool designed to offer lucid, chronological, and summarized insights into Indian policy issues. PolicyStory collects news articles from diverse sources, clusters them by topic, and generates three levels of summaries from longitudinal media discourse on policies, leveraging open source large language models. A user study around the tool indicated that PolicyStory effectively aided users in grasping policy developments over time, with positive feedback highlighting its usability and clarity of summaries. By providing users a birds' eye view of complex policy topics, PolicyStory serves as a valuable resource.

Problem

• Generating structured summaries of Indian policy news
• Addressing information overload in sociopolitical news consumption
• Providing chronological insights into policy developments over time

Innovation

• Leveraging open source large language models
• Clustering news articles by topic
• Generating three-level chronological policy summaries