{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7O2JLAY5LFJXR3SUD2ERFBMSWF","short_pith_number":"pith:7O2JLAY5","schema_version":"1.0","canonical_sha256":"fbb495831d595378ee541e89128592b14ab04b648d8878a092d36fcd4928f84a","source":{"kind":"arxiv","id":"1707.00621","version":1},"attestation_state":"computed","paper":{"title":"Including Dialects and Language Varieties in Author Profiling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alina Maria Ciobanu, Liviu P. Dinu, Marcos Zampieri, Shervin Malmasi","submitted_at":"2017-07-03T16:06:16Z","abstract_excerpt":"This paper presents a computational approach to author profiling taking gender and language variety into account. We apply an ensemble system with the output of multiple linear SVM classifiers trained on character and word $n$-grams. We evaluate the system using the dataset provided by the organizers of the 2017 PAN lab on author profiling. Our approach achieved 75% average accuracy on gender identification on tweets written in four languages and 97% accuracy on language variety identification for Portuguese."},"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":"1707.00621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-03T16:06:16Z","cross_cats_sorted":[],"title_canon_sha256":"b6a53481552e5174308203987953123847f367aba3bc12135fa3847e7b5ebc05","abstract_canon_sha256":"ee5da8f622464a3347cbcf8d0ecca2bb1e59f183ace5debbe68e9e1a89a2e8a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:02.875020Z","signature_b64":"vHiAv/wKtDx4bDTfxM57z7ibC7t6OcACZlPCMq+eFik3lzR8+P2f3R2LpJknN6FoyqFyW6QjpHAAVQ8qxHJCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb495831d595378ee541e89128592b14ab04b648d8878a092d36fcd4928f84a","last_reissued_at":"2026-05-18T00:41:02.874281Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:02.874281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Including Dialects and Language Varieties in Author Profiling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alina Maria Ciobanu, Liviu P. Dinu, Marcos Zampieri, Shervin Malmasi","submitted_at":"2017-07-03T16:06:16Z","abstract_excerpt":"This paper presents a computational approach to author profiling taking gender and language variety into account. We apply an ensemble system with the output of multiple linear SVM classifiers trained on character and word $n$-grams. We evaluate the system using the dataset provided by the organizers of the 2017 PAN lab on author profiling. Our approach achieved 75% average accuracy on gender identification on tweets written in four languages and 97% accuracy on language variety identification for Portuguese."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00621","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":"1707.00621","created_at":"2026-05-18T00:41:02.874410+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.00621v1","created_at":"2026-05-18T00:41:02.874410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00621","created_at":"2026-05-18T00:41:02.874410+00:00"},{"alias_kind":"pith_short_12","alias_value":"7O2JLAY5LFJX","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7O2JLAY5LFJXR3SU","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7O2JLAY5","created_at":"2026-05-18T12:31:05.417338+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/7O2JLAY5LFJXR3SUD2ERFBMSWF","json":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF.json","graph_json":"https://pith.science/api/pith-number/7O2JLAY5LFJXR3SUD2ERFBMSWF/graph.json","events_json":"https://pith.science/api/pith-number/7O2JLAY5LFJXR3SUD2ERFBMSWF/events.json","paper":"https://pith.science/paper/7O2JLAY5"},"agent_actions":{"view_html":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF","download_json":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF.json","view_paper":"https://pith.science/paper/7O2JLAY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.00621&json=true","fetch_graph":"https://pith.science/api/pith-number/7O2JLAY5LFJXR3SUD2ERFBMSWF/graph.json","fetch_events":"https://pith.science/api/pith-number/7O2JLAY5LFJXR3SUD2ERFBMSWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/action/storage_attestation","attest_author":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/action/author_attestation","sign_citation":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/action/citation_signature","submit_replication":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/action/replication_record"}},"created_at":"2026-05-18T00:41:02.874410+00:00","updated_at":"2026-05-18T00:41:02.874410+00:00"}