{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/effective-hierarchical-information-threading","title":"Effective Hierarchical Information Threading Using Network Community Detection","arxiv_id":null,"date":"2023-03-17","proceeding":"European Conference on Information Retrieval 2023 3","authors":["Hitarth Narvala","Graham McDonald","Iadh Ounis"],"abstract":"With the tremendous growth in the volume of information produced online every day (e.g. news articles), there is a need for automatic methods to identify related information about events as the events evolve over time (i.e., information threads). In this work, we propose a novel unsupervised approach, called HINT, which identifies coherent Hierarchical Information Threads. These threads can enable users to easily interpret a hierarchical association of diverse evolving information about an event or discussion. In particular, HINT deploys a scalable architecture based on network community detection to effectively identify hierarchical links between documents based on their chronological relatedness and answers to the 5W1H questions (i.e., who, what, where, when, why & how). On the NewSHead collection, we show that HINT markedly outperforms existing state-of-the-art approaches in terms of the quality of the identified threads. We also conducted a user study that shows that our proposed network-based hierarchical threads are significantly (p<0.05) preferred by users compared to cluster-based sequential threads.","url_abs":"https://link.springer.com/chapter/10.1007/978-3-031-28244-7_44","url_pdf":"https://doi.org/10.1007/978-3-031-28244-7_44","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"effective-hierarchical-information-threading","repo_url":"https://github.com/hitt08/HINT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"community-detection","task_name":"Community Detection"},{"task_slug":"event-extraction","task_name":"Event Extraction"},{"task_slug":"information-threading","task_name":"Information Threading"}],"methods":[],"datasets_introduced":[],"methods_introduced":[{"slug":"hint","name":"HINT","full_name":"Hierarchical Information Threading"}],"results":[{"leaderboard":"/sota/information-threading-on-newshead","task":"Information Threading","dataset":"NewSHead","model":"HINT","rank_in_archive_order":1,"of":4,"metrics":{"NMI":"0.797"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}