{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JE3YB7HZ3IAFQXWSQFONTBO2VC","short_pith_number":"pith:JE3YB7HZ","schema_version":"1.0","canonical_sha256":"493780fcf9da00585ed2815cd985daa8bffb9244e9caf7e7a2274a11379fa07e","source":{"kind":"arxiv","id":"1906.06465","version":2},"attestation_state":"computed","paper":{"title":"Correlating Twitter Language with Community-Level Health Outcomes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SI","stat.ML"],"primary_cat":"cs.CL","authors_text":"Arno Schneuwly, Mark Cieliebak, Martin Jaggi, Ralf Grubenmann, S\\'everine Rion Logean","submitted_at":"2019-06-13T01:42:23Z","abstract_excerpt":"We study how language on social media is linked to diseases such as atherosclerotic heart disease (AHD), diabetes and various types of cancer. Our proposed model leverages state-of-the-art sentence embeddings, followed by a regression model and clustering, without the need of additional labelled data. It allows to predict community-level medical outcomes from language, and thereby potentially translate these to the individual level. The method is applicable to a wide range of target variables and allows us to discover known and potentially novel correlations of medical outcomes with life-style"},"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":"1906.06465","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-13T01:42:23Z","cross_cats_sorted":["cs.LG","cs.SI","stat.ML"],"title_canon_sha256":"63e7596e6e954a665165d85ba6e86875c8628a1f948dbe14795d1df283ae4da3","abstract_canon_sha256":"884c422d83db8d5a2ad5794f0e152194a3c6504f1f04c43ff94fa957f4cfb210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:41.339556Z","signature_b64":"ro9BTVLTSlh2xhxyP70EO75Sax4p8v4SW7U4Qtot9DgbTbuMyAvfT3XWxXbSYTy1nA/WlzqkPJONY16faj4iDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"493780fcf9da00585ed2815cd985daa8bffb9244e9caf7e7a2274a11379fa07e","last_reissued_at":"2026-05-17T23:42:41.338862Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:41.338862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correlating Twitter Language with Community-Level Health Outcomes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SI","stat.ML"],"primary_cat":"cs.CL","authors_text":"Arno Schneuwly, Mark Cieliebak, Martin Jaggi, Ralf Grubenmann, S\\'everine Rion Logean","submitted_at":"2019-06-13T01:42:23Z","abstract_excerpt":"We study how language on social media is linked to diseases such as atherosclerotic heart disease (AHD), diabetes and various types of cancer. Our proposed model leverages state-of-the-art sentence embeddings, followed by a regression model and clustering, without the need of additional labelled data. It allows to predict community-level medical outcomes from language, and thereby potentially translate these to the individual level. The method is applicable to a wide range of target variables and allows us to discover known and potentially novel correlations of medical outcomes with life-style"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06465","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":""},"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":"1906.06465","created_at":"2026-05-17T23:42:41.338969+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06465v2","created_at":"2026-05-17T23:42:41.338969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06465","created_at":"2026-05-17T23:42:41.338969+00:00"},{"alias_kind":"pith_short_12","alias_value":"JE3YB7HZ3IAF","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"JE3YB7HZ3IAFQXWS","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"JE3YB7HZ","created_at":"2026-05-18T12:33:18.533446+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/JE3YB7HZ3IAFQXWSQFONTBO2VC","json":"https://pith.science/pith/JE3YB7HZ3IAFQXWSQFONTBO2VC.json","graph_json":"https://pith.science/api/pith-number/JE3YB7HZ3IAFQXWSQFONTBO2VC/graph.json","events_json":"https://pith.science/api/pith-number/JE3YB7HZ3IAFQXWSQFONTBO2VC/events.json","paper":"https://pith.science/paper/JE3YB7HZ"},"agent_actions":{"view_html":"https://pith.science/pith/JE3YB7HZ3IAFQXWSQFONTBO2VC","download_json":"https://pith.science/pith/JE3YB7HZ3IAFQXWSQFONTBO2VC.json","view_paper":"https://pith.science/paper/JE3YB7HZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06465&json=true","fetch_graph":"https://pith.science/api/pith-number/JE3YB7HZ3IAFQXWSQFONTBO2VC/graph.json","fetch_events":"https://pith.science/api/pith-number/JE3YB7HZ3IAFQXWSQFONTBO2VC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JE3YB7HZ3IAFQXWSQFONTBO2VC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JE3YB7HZ3IAFQXWSQFONTBO2VC/action/storage_attestation","attest_author":"https://pith.science/pith/JE3YB7HZ3IAFQXWSQFONTBO2VC/action/author_attestation","sign_citation":"https://pith.science/pith/JE3YB7HZ3IAFQXWSQFONTBO2VC/action/citation_signature","submit_replication":"https://pith.science/pith/JE3YB7HZ3IAFQXWSQFONTBO2VC/action/replication_record"}},"created_at":"2026-05-17T23:42:41.338969+00:00","updated_at":"2026-05-17T23:42:41.338969+00:00"}