{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S4GRXBGQHTALLL2TNFBMYVOBEH","short_pith_number":"pith:S4GRXBGQ","schema_version":"1.0","canonical_sha256":"970d1b84d03cc0b5af536942cc55c121e66e646ad82e3a6c0ab3b8b27c0dba14","source":{"kind":"arxiv","id":"2201.08277","version":3},"attestation_state":"computed","paper":{"title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alipio Jeorge, Anuoluwapo Aremu, Bello Shehu Bello, Chris Chinenye Emezue, David Ifeoluwa Adelani, Ibrahim Said Ahmad, Idris Abdulmumin, Monojit Choudhury, Pavel Brazdil, Saheed Salahudeen Abdullahi, Sebastian Ruder, Shamsuddeen Hassan Muhammad","submitted_at":"2022-01-20T16:28:06Z","abstract_excerpt":"Sentiment analysis is one of the most widely studied applications in NLP, but most work focuses on languages with large amounts of data. We introduce the first large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria (Hausa, Igbo, Nigerian-Pidgin, and Yor\\`ub\\'a ) consisting of around 30,000 annotated tweets per language (and 14,000 for Nigerian-Pidgin), including a significant fraction of code-mixed tweets. We propose text collection, filtering, processing and labeling methods that enable us to create datasets for these low-resource languages."},"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":"2201.08277","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T16:28:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"773d8fa0f42a8c2562bf80523f48ccc5315b3bffca2e80c6986dbba4c3203215","abstract_canon_sha256":"bec43545d7be0a82c87823d593d91320069f82946ce1425dc1485c21e532e787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:54.936209Z","signature_b64":"hOnYhJzg36x5Vwjrx8uBvahKnvPx18hEnvKDjWiMkbAB3wowxuFjFxq5bandM4SsjDAVCTdUG8xOmc6ERg/FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"970d1b84d03cc0b5af536942cc55c121e66e646ad82e3a6c0ab3b8b27c0dba14","last_reissued_at":"2026-07-05T04:32:54.935690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:54.935690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alipio Jeorge, Anuoluwapo Aremu, Bello Shehu Bello, Chris Chinenye Emezue, David Ifeoluwa Adelani, Ibrahim Said Ahmad, Idris Abdulmumin, Monojit Choudhury, Pavel Brazdil, Saheed Salahudeen Abdullahi, Sebastian Ruder, Shamsuddeen Hassan Muhammad","submitted_at":"2022-01-20T16:28:06Z","abstract_excerpt":"Sentiment analysis is one of the most widely studied applications in NLP, but most work focuses on languages with large amounts of data. We introduce the first large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria (Hausa, Igbo, Nigerian-Pidgin, and Yor\\`ub\\'a ) consisting of around 30,000 annotated tweets per language (and 14,000 for Nigerian-Pidgin), including a significant fraction of code-mixed tweets. We propose text collection, filtering, processing and labeling methods that enable us to create datasets for these low-resource languages."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08277","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.08277/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2201.08277","created_at":"2026-07-05T04:32:54.935759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08277v3","created_at":"2026-07-05T04:32:54.935759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08277","created_at":"2026-07-05T04:32:54.935759+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4GRXBGQHTAL","created_at":"2026-07-05T04:32:54.935759+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4GRXBGQHTALLL2T","created_at":"2026-07-05T04:32:54.935759+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4GRXBGQ","created_at":"2026-07-05T04:32:54.935759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20255","citing_title":"The Register Gap: A Meaning Intelligence Framework for Nigerian Public Discourse","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09955","citing_title":"Beyond Majority Voting: Agreement-Based Clustering to Model Annotator Perspectives in Subjective NLP Tasks","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH","json":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH.json","graph_json":"https://pith.science/api/pith-number/S4GRXBGQHTALLL2TNFBMYVOBEH/graph.json","events_json":"https://pith.science/api/pith-number/S4GRXBGQHTALLL2TNFBMYVOBEH/events.json","paper":"https://pith.science/paper/S4GRXBGQ"},"agent_actions":{"view_html":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH","download_json":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH.json","view_paper":"https://pith.science/paper/S4GRXBGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08277&json=true","fetch_graph":"https://pith.science/api/pith-number/S4GRXBGQHTALLL2TNFBMYVOBEH/graph.json","fetch_events":"https://pith.science/api/pith-number/S4GRXBGQHTALLL2TNFBMYVOBEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH/action/storage_attestation","attest_author":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH/action/author_attestation","sign_citation":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH/action/citation_signature","submit_replication":"https://pith.science/pith/S4GRXBGQHTALLL2TNFBMYVOBEH/action/replication_record"}},"created_at":"2026-07-05T04:32:54.935759+00:00","updated_at":"2026-07-05T04:32:54.935759+00:00"}