{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:37USK235MUZQ5QF35LU7MP5E53","short_pith_number":"pith:37USK235","schema_version":"1.0","canonical_sha256":"dfe9256b7d65330ec0bbeae9f63fa4eedde1484d0c7311fbfd132526087962de","source":{"kind":"arxiv","id":"1802.05322","version":1},"attestation_state":"computed","paper":{"title":"Classifying movie genres by analyzing text reviews","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Nyberg","submitted_at":"2018-02-14T21:04:15Z","abstract_excerpt":"This paper proposes a method for classifying movie genres by only looking at text reviews. The data used are from Large Movie Review Dataset v1.0 and IMDb. This paper compared a K-nearest neighbors (KNN) model and a multilayer perceptron (MLP) that uses tf-idf as input features. The paper also discusses different evaluation metrics used when doing multi-label classification. For the data used in this research, the KNN model performed the best with an accuracy of 55.4\\% and a Hamming loss of 0.047."},"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":"1802.05322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-14T21:04:15Z","cross_cats_sorted":[],"title_canon_sha256":"96321d20fb5b5e8703ac16b7e34803ee9ed0347abbda9f57219adc5373f28955","abstract_canon_sha256":"a96889e63a8a3cd3e2bf07214e1d8fb0bbee11cdf8b9f40fc703cfd3f5154b2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:15.985578Z","signature_b64":"1JM+fvrr/8ES3ZTnoApc6pHsaiVoVrfTzEejfiaM82xSvVhlCZjewzjSv1uufua36vNVS29rt7entHQSPoJVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfe9256b7d65330ec0bbeae9f63fa4eedde1484d0c7311fbfd132526087962de","last_reissued_at":"2026-05-18T00:23:15.985027Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:15.985027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classifying movie genres by analyzing text reviews","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Nyberg","submitted_at":"2018-02-14T21:04:15Z","abstract_excerpt":"This paper proposes a method for classifying movie genres by only looking at text reviews. The data used are from Large Movie Review Dataset v1.0 and IMDb. This paper compared a K-nearest neighbors (KNN) model and a multilayer perceptron (MLP) that uses tf-idf as input features. The paper also discusses different evaluation metrics used when doing multi-label classification. For the data used in this research, the KNN model performed the best with an accuracy of 55.4\\% and a Hamming loss of 0.047."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05322","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":"1802.05322","created_at":"2026-05-18T00:23:15.985128+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05322v1","created_at":"2026-05-18T00:23:15.985128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05322","created_at":"2026-05-18T00:23:15.985128+00:00"},{"alias_kind":"pith_short_12","alias_value":"37USK235MUZQ","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"37USK235MUZQ5QF3","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"37USK235","created_at":"2026-05-18T12:32:02.567920+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/37USK235MUZQ5QF35LU7MP5E53","json":"https://pith.science/pith/37USK235MUZQ5QF35LU7MP5E53.json","graph_json":"https://pith.science/api/pith-number/37USK235MUZQ5QF35LU7MP5E53/graph.json","events_json":"https://pith.science/api/pith-number/37USK235MUZQ5QF35LU7MP5E53/events.json","paper":"https://pith.science/paper/37USK235"},"agent_actions":{"view_html":"https://pith.science/pith/37USK235MUZQ5QF35LU7MP5E53","download_json":"https://pith.science/pith/37USK235MUZQ5QF35LU7MP5E53.json","view_paper":"https://pith.science/paper/37USK235","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05322&json=true","fetch_graph":"https://pith.science/api/pith-number/37USK235MUZQ5QF35LU7MP5E53/graph.json","fetch_events":"https://pith.science/api/pith-number/37USK235MUZQ5QF35LU7MP5E53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37USK235MUZQ5QF35LU7MP5E53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37USK235MUZQ5QF35LU7MP5E53/action/storage_attestation","attest_author":"https://pith.science/pith/37USK235MUZQ5QF35LU7MP5E53/action/author_attestation","sign_citation":"https://pith.science/pith/37USK235MUZQ5QF35LU7MP5E53/action/citation_signature","submit_replication":"https://pith.science/pith/37USK235MUZQ5QF35LU7MP5E53/action/replication_record"}},"created_at":"2026-05-18T00:23:15.985128+00:00","updated_at":"2026-05-18T00:23:15.985128+00:00"}