{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QLGIULGGIO5RUZNDW7RRBBN7UC","short_pith_number":"pith:QLGIULGG","schema_version":"1.0","canonical_sha256":"82cc8a2cc643bb1a65a3b7e31085bfa09238a7adad6adc6f5b8c3f1cbc5edad1","source":{"kind":"arxiv","id":"2301.11508","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.11508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T03:00:46Z","cross_cats_sorted":[],"title_canon_sha256":"b5c4c25924eaafd1caf024db90daed0e0e9289dad98354a202cf7e7248482a15","abstract_canon_sha256":"0dcda19c7220c8476c1e7d8596094e7ce7b920e9735afc571e68cf97715dca44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:39.982219Z","signature_b64":"loepg6SC497ukY2c/9qUFhgnI2kySvLLCx7rmC/3RZZyGzUcJv1QCXLY/ZPev8rt/GncpDg6c41gjBc9ArXFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82cc8a2cc643bb1a65a3b7e31085bfa09238a7adad6adc6f5b8c3f1cbc5edad1","last_reissued_at":"2026-07-05T06:14:39.981792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:39.981792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.11508","created_at":"2026-07-05T06:14:39.981848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11508v2","created_at":"2026-07-05T06:14:39.981848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11508","created_at":"2026-07-05T06:14:39.981848+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLGIULGGIO5R","created_at":"2026-07-05T06:14:39.981848+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLGIULGGIO5RUZND","created_at":"2026-07-05T06:14:39.981848+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLGIULGG","created_at":"2026-07-05T06:14:39.981848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC","json":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC.json","graph_json":"https://pith.science/api/pith-number/QLGIULGGIO5RUZNDW7RRBBN7UC/graph.json","events_json":"https://pith.science/api/pith-number/QLGIULGGIO5RUZNDW7RRBBN7UC/events.json","paper":"https://pith.science/paper/QLGIULGG"},"agent_actions":{"view_html":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC","download_json":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC.json","view_paper":"https://pith.science/paper/QLGIULGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11508&json=true","fetch_graph":"https://pith.science/api/pith-number/QLGIULGGIO5RUZNDW7RRBBN7UC/graph.json","fetch_events":"https://pith.science/api/pith-number/QLGIULGGIO5RUZNDW7RRBBN7UC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC/action/storage_attestation","attest_author":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC/action/author_attestation","sign_citation":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC/action/citation_signature","submit_replication":"https://pith.science/pith/QLGIULGGIO5RUZNDW7RRBBN7UC/action/replication_record"}},"created_at":"2026-07-05T06:14:39.981848+00:00","updated_at":"2026-07-05T06:14:39.981848+00:00"}