Who's important? -- SUnSET: Synergistic Understanding of Stakeholder, Events and Time for Timeline Generation

2025-07-29

AI Summary

Existing news timeline generation methods rely solely on textual similarity and temporal proximity, overlooking stakeholders’ pivotal role in event evolution. To address this, we propose SUnSET—a novel framework that explicitly models the Stakeholder-Event-Time (SET) triad. SUnSET leverages large language models to accurately extract cross-source SET triples, constructs a stakeholder-aware heterogeneous event graph, and introduces a Relevancy ranking mechanism grounded in entity associations and information propagation paths—enabling joint assessment of event importance and dynamic temporal progression. Evaluated on standard timeline summarization benchmarks, SUnSET significantly outperforms all baselines. Results demonstrate that explicit stakeholder modeling substantially enhances both the accuracy and interpretability of multi-source news event understanding.

Technology Category

• Natural Language Processing: Information Extraction
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

As news reporting becomes increasingly global and decentralized online, tracking related events across multiple sources presents significant challenges. Existing news summarization methods typically utilizes Large Language Models and Graphical methods on article-based summaries. However, this is not effective since it only considers the textual content of similarly dated articles to understand the gist of the event. To counteract the lack of analysis on the parties involved, it is essential to come up with a novel framework to gauge the importance of stakeholders and the connection of related events through the relevant entities involved. Therefore, we present SUnSET: Synergistic Understanding of Stakeholder, Events and Time for the task of Timeline Summarization (TLS). We leverage powerful Large Language Models (LLMs) to build SET triplets and introduced the use of stakeholder-based ranking to construct a $Relevancy$ metric, which can be extended into general situations. Our experimental results outperform all prior baselines and emerged as the new State-of-the-Art, highlighting the impact of stakeholder information within news article.

Problem

• Tracking related events across multiple decentralized news sources
• Analyzing stakeholder importance and event connections in news
• Improving timeline summarization with stakeholder-based ranking metrics

Innovation

• Leverages LLMs to build SET triplets
• Introduces stakeholder-based ranking metric
• Synergistic analysis of stakeholders, events, time