{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WK7LGDPUAHDBZQ3Q23L5W5ZYGI","short_pith_number":"pith:WK7LGDPU","schema_version":"1.0","canonical_sha256":"b2beb30df401c61cc370d6d7db773832172c0f32d5194b3bf77b880fd1653a01","source":{"kind":"arxiv","id":"1803.05495","version":1},"attestation_state":"computed","paper":{"title":"Challenges in Discriminating Profanity from Hate Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcos Zampieri, Shervin Malmasi","submitted_at":"2018-03-14T20:00:08Z","abstract_excerpt":"In this study we approach the problem of distinguishing general profanity from hate speech in social media, something which has not been widely considered. Using a new dataset annotated specifically for this task, we employ supervised classification along with a set of features that includes n-grams, skip-grams and clustering-based word representations. We apply approaches based on single classifiers as well as more advanced ensemble classifiers and stacked generalization, achieving the best result of 80% accuracy for this 3-class classification task. Analysis of the results reveals that discr"},"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":"1803.05495","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-14T20:00:08Z","cross_cats_sorted":[],"title_canon_sha256":"d4dadbe7cd974c07494bb0d52186ee579947071a0ef92b945834efb0a34d7f2b","abstract_canon_sha256":"2bc6475803e619181bca506b1eb8d159b26e0312a328d19cb7ea6f93f7def898"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:55.326892Z","signature_b64":"Yv1bn6AY6ca1Haful0pRaEkynBuidmGElQwj0Br/+0X1PbaEMGfM6Ogr7myuYa5nu6swIzD8uO26Lp0EHw7FBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2beb30df401c61cc370d6d7db773832172c0f32d5194b3bf77b880fd1653a01","last_reissued_at":"2026-05-18T00:20:55.326433Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:55.326433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenges in Discriminating Profanity from Hate Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcos Zampieri, Shervin Malmasi","submitted_at":"2018-03-14T20:00:08Z","abstract_excerpt":"In this study we approach the problem of distinguishing general profanity from hate speech in social media, something which has not been widely considered. Using a new dataset annotated specifically for this task, we employ supervised classification along with a set of features that includes n-grams, skip-grams and clustering-based word representations. We apply approaches based on single classifiers as well as more advanced ensemble classifiers and stacked generalization, achieving the best result of 80% accuracy for this 3-class classification task. Analysis of the results reveals that discr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05495","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":"1803.05495","created_at":"2026-05-18T00:20:55.326500+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.05495v1","created_at":"2026-05-18T00:20:55.326500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05495","created_at":"2026-05-18T00:20:55.326500+00:00"},{"alias_kind":"pith_short_12","alias_value":"WK7LGDPUAHDB","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WK7LGDPUAHDBZQ3Q","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WK7LGDPU","created_at":"2026-05-18T12:32:59.047623+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/WK7LGDPUAHDBZQ3Q23L5W5ZYGI","json":"https://pith.science/pith/WK7LGDPUAHDBZQ3Q23L5W5ZYGI.json","graph_json":"https://pith.science/api/pith-number/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/graph.json","events_json":"https://pith.science/api/pith-number/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/events.json","paper":"https://pith.science/paper/WK7LGDPU"},"agent_actions":{"view_html":"https://pith.science/pith/WK7LGDPUAHDBZQ3Q23L5W5ZYGI","download_json":"https://pith.science/pith/WK7LGDPUAHDBZQ3Q23L5W5ZYGI.json","view_paper":"https://pith.science/paper/WK7LGDPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.05495&json=true","fetch_graph":"https://pith.science/api/pith-number/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/graph.json","fetch_events":"https://pith.science/api/pith-number/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/action/storage_attestation","attest_author":"https://pith.science/pith/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/action/author_attestation","sign_citation":"https://pith.science/pith/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/action/citation_signature","submit_replication":"https://pith.science/pith/WK7LGDPUAHDBZQ3Q23L5W5ZYGI/action/replication_record"}},"created_at":"2026-05-18T00:20:55.326500+00:00","updated_at":"2026-05-18T00:20:55.326500+00:00"}