{"paper":{"title":"Theme-driven Keyphrase Extraction to Analyze Social Media Discourse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Joseph Gatto, Madhusudan Basak, Omar Sharif, Sarah Preum, William Romano","submitted_at":"2023-01-27T03:00:46Z","abstract_excerpt":"Social media platforms are vital resources for sharing self-reported health experiences, offering rich data on various health topics. Despite advancements in Natural Language Processing (NLP) enabling large-scale social media data analysis, a gap remains in applying keyphrase extraction to health-related content. Keyphrase extraction is used to identify salient concepts in social media discourse without being constrained by predefined entity classes. This paper introduces a theme-driven keyphrase extraction framework tailored for social media, a pioneering approach designed to capture clinical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11508","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.11508/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}