{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MNROH535DY5KRB5F2T4FWIKGN3","short_pith_number":"pith:MNROH535","schema_version":"1.0","canonical_sha256":"6362e3f77d1e3aa887a5d4f85b21466efd5d86023478663cdadd06e08f89b524","source":{"kind":"arxiv","id":"1901.00439","version":1},"attestation_state":"computed","paper":{"title":"Deep Representation Learning for Clustering of Health Tweets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Oguzhan Gencoglu","submitted_at":"2018-12-25T00:31:22Z","abstract_excerpt":"Twitter has been a prominent social media platform for mining population-level health data and accurate clustering of health-related tweets into topics is important for extracting relevant health insights. In this work, we propose deep convolutional autoencoders for learning compact representations of health-related tweets, further to be employed in clustering. We compare our method to several conventional tweet representation methods including bag-of-words, term frequency-inverse document frequency, Latent Dirichlet Allocation and Non-negative Matrix Factorization with 3 different clustering "},"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":"1901.00439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-25T00:31:22Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"ea0a16c51c5cffdcd3e6699e4791cd13732a32be79c317408ee1724f79aa3f9e","abstract_canon_sha256":"bea7174fc4479c1d5952e8b028e6b0461bfad06ef4a10ef50ffb6a0fa935c301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:03.859960Z","signature_b64":"uzffVGohuNyUMGsDOgACCds2lrgNyrUDxm2bfryRV4xkRwDcjJJXaOAv2T+8yUbmNQP87b9LdSTCPzRbjGusCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6362e3f77d1e3aa887a5d4f85b21466efd5d86023478663cdadd06e08f89b524","last_reissued_at":"2026-05-17T23:57:03.859356Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:03.859356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Representation Learning for Clustering of Health Tweets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Oguzhan Gencoglu","submitted_at":"2018-12-25T00:31:22Z","abstract_excerpt":"Twitter has been a prominent social media platform for mining population-level health data and accurate clustering of health-related tweets into topics is important for extracting relevant health insights. In this work, we propose deep convolutional autoencoders for learning compact representations of health-related tweets, further to be employed in clustering. We compare our method to several conventional tweet representation methods including bag-of-words, term frequency-inverse document frequency, Latent Dirichlet Allocation and Non-negative Matrix Factorization with 3 different clustering "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.00439","kind":"arxiv","version":1},"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":"1901.00439","created_at":"2026-05-17T23:57:03.859475+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.00439v1","created_at":"2026-05-17T23:57:03.859475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.00439","created_at":"2026-05-17T23:57:03.859475+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNROH535DY5K","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNROH535DY5KRB5F","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNROH535","created_at":"2026-05-18T12:32:37.024351+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/MNROH535DY5KRB5F2T4FWIKGN3","json":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3.json","graph_json":"https://pith.science/api/pith-number/MNROH535DY5KRB5F2T4FWIKGN3/graph.json","events_json":"https://pith.science/api/pith-number/MNROH535DY5KRB5F2T4FWIKGN3/events.json","paper":"https://pith.science/paper/MNROH535"},"agent_actions":{"view_html":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3","download_json":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3.json","view_paper":"https://pith.science/paper/MNROH535","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.00439&json=true","fetch_graph":"https://pith.science/api/pith-number/MNROH535DY5KRB5F2T4FWIKGN3/graph.json","fetch_events":"https://pith.science/api/pith-number/MNROH535DY5KRB5F2T4FWIKGN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/action/storage_attestation","attest_author":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/action/author_attestation","sign_citation":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/action/citation_signature","submit_replication":"https://pith.science/pith/MNROH535DY5KRB5F2T4FWIKGN3/action/replication_record"}},"created_at":"2026-05-17T23:57:03.859475+00:00","updated_at":"2026-05-17T23:57:03.859475+00:00"}