EMNLP Findings2023
Using LLM for Improving Key Event Discovery: Temporal-Guided News Stream Clustering with Event Summaries
Nishanth Sridhar Nakshatri, Siyi Liu, Sihao Chen, Dan Roth, Dan Goldwasser, Daniel Hopkins
Abstract
Understanding and characterizing the discussions around key events in news streams is important for analyzing political discourse. In this work, we study the problem of identification of such key events and the news articles associated with those events from news streams. We propose a generic framework for news stream clustering that analyzes the temporal trend of news articles to automatically extract the underlying key news events that draw significant media attention. We characterize such key events by generating event summaries, based on which we form document clusters in an unsupervised fashion. We evaluate our simple yet effective framework, and show that it produces more coherent event-focused clusters. To demonstrate the utility of our approach, and facilitate future research along the line, we use our framework to construct KEYEVENTS 1 , a dataset of 40k articles with 611 key events from 11 topics.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
5 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections cites Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence
- Summaries as Centroids for Interpretable and Scalable Text Clustering cites Language Models are Few-Shot Learners
- What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection cites Language Models are Few-Shot Learners
Cited by top-tier papers5
- What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot DetectionShangbin Feng, Herun Wan, Ningnan Wang, Zhaoxuan Tan et al.ACL 2024 · 19 citations
- Summaries as Centroids for Interpretable and Scalable Text ClusteringJairo Diaz RodriguezICLR 2026 · 11 citations
- CoMaPOI: A Collaborative Multi-Agent Framework for Next POI Prediction Bridging the Gap Between Trajectory and LanguageLin Zhong, Lingzhi Wang, Xu Yang, Qing LiaoSIGIR 2025 · 6 citations
- Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document StreamsYukyung Lee, Yebin Lim, Woojun Jung, Wonjun Choi et al.KDD 2026
- Tracking the Takes and Trajectories of English-Language News Narratives across Trustworthy and Worrisome WebsitesHans W. A. Hanley, Emily Okabe, Zakir DurumericUSENIX Security 2025
Builds on5
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Is Automated Topic Model Evaluation Broken? The Incoherence of CoherenceAlexander Miserlis Hoyle, Pranav Goel, Andrew Hian-Cheong, Denis Peskov et al.NeurIPS 2021 · 220 citations
- Large Dual Encoders Are Generalizable RetrieversJianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai et al.EMNLP 2022 · 145 citations
- Sentence-level Media Bias Analysis Informed by Discourse StructuresYuanyuan Lei, Ruihong Huang, Lu Wang, Nick BeauchampEMNLP 2022 · 22 citations
- Interactive Concept Learning for Uncovering Latent Themes in Large Text CollectionsMaria Leonor Pacheco, Tunazzina Islam, Lyle H. Ungar, Ming Yin et al.ACL Findings 2023 · 5 citations
Related papers
- When it Rains, it Pours: Modeling Media Storms and the News EcosystemBenjamin Litterer, David Jurgens, Dallas CardEMNLP Findings 2023 · 4 citations
- Timeline Summarization based on Event Graph Compression via Time-Aware Optimal TransportManling Li, Tengfei Ma, Mo Yu, Lingfei Wu et al.EMNLP 2021 · 25 citations
- Enhancing Event-centric News Cluster Summarization via Data Sharpening and Localization InsightsLongyin Zhang, Bowei Zou, AiTi AwACL 2025 · 1 citation
- Talking Point based Ideological Discourse Analysis in News EventsNishanth Sridhar Nakshatri, Nikhil Mehta, Siyi Liu, Sihao Chen et al.ACL Findings 2025
- Unsupervised Key Event Detection from Massive Text CorporaYunyi Zhang, Fang Guo, Jiaming Shen, Jiawei HanKDD 2022 · 14 citations
