{"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/sub-event-detection-from-twitter-streams-as-a","title":"Sub-event detection from Twitter streams as a sequence labeling problem","arxiv_id":"1903.05396","date":"2019-03-13","proceeding":"NAACL 2019 6","authors":["Giannis Bekoulis","Johannes Deleu","Thomas Demeester","Chris Develder"],"abstract":"This paper introduces improved methods for sub-event detection in social\nmedia streams, by applying neural sequence models not only on the level of\nindividual posts, but also directly on the stream level. Current approaches to\nidentify sub-events within a given event, such as a goal during a soccer match,\nessentially do not exploit the sequential nature of social media streams. We\naddress this shortcoming by framing the sub-event detection problem in social\nmedia streams as a sequence labeling task and adopt a neural sequence\narchitecture that explicitly accounts for the chronological order of posts.\nSpecifically, we (i) establish a neural baseline that outperforms a graph-based\nstate-of-the-art method for binary sub-event detection (2.7% micro-F1\nimprovement), as well as (ii) demonstrate superiority of a recurrent neural\nnetwork model on the posts sequence level for labeled sub-events (2.4%\nbin-level F1 improvement over non-sequential models).","url_abs":"http://arxiv.org/abs/1903.05396v1","url_pdf":"http://arxiv.org/pdf/1903.05396v1.pdf","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":"sub-event-detection-from-twitter-streams-as-a","repo_url":"https://github.com/bekou/subevent_sequence_labeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"event-detection","task_name":"Event Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.05396","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}