{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3KCTUIO3HFY5CCD5QIL4GQSOWC","short_pith_number":"pith:3KCTUIO3","schema_version":"1.0","canonical_sha256":"da853a21db3971d1087d8217c3424eb09c9a91afdb401fffbcb3a43fd1c5b727","source":{"kind":"arxiv","id":"2202.04725","version":1},"attestation_state":"computed","paper":{"title":"TamilEmo: Finegrained Emotion Detection Dataset for Tamil","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anbukkarasi Sampath, Bharathi Raja Chakravarthi, Charangan Vasantharajan, John Phillip McCrae, Kanchana Sivanraju, Prasanna Kumar Kumarasen, Rahul Ponnusamy, Ruba Priyadharshini, Sathiyaraj Thangasamy, Sean Benhur, Thenmozhi Durairaj","submitted_at":"2022-02-09T21:05:28Z","abstract_excerpt":"Emotional Analysis from textual input has been considered both a challenging and interesting task in Natural Language Processing. However, due to the lack of datasets in low-resource languages (i.e. Tamil), it is difficult to conduct research of high standard in this area. Therefore we introduce this labelled dataset (a largest manually annotated dataset of more than 42k Tamil YouTube comments, labelled for 31 emotions including neutral) for emotion recognition. The goal of this dataset is to improve emotion detection in multiple downstream tasks in Tamil. We have also created three different "},"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":"2202.04725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-09T21:05:28Z","cross_cats_sorted":[],"title_canon_sha256":"1d5b040a2cfa14b1144a417bc0d382a0eda71c627fcbffb275b5a9c3aebe0437","abstract_canon_sha256":"1bff5a5aab7ec45716275517bfefdaba3de22fedc2fa989a394c60caa8acc4b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:53.267701Z","signature_b64":"+ItycLCdsVEkZtI6D90iL1sDwMNtuhhBu9ptmhioxsBniLZtSYNdQxQd5RDhGy3Ry0ma6Qu0otEvbbqjWxL1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da853a21db3971d1087d8217c3424eb09c9a91afdb401fffbcb3a43fd1c5b727","last_reissued_at":"2026-07-05T03:55:53.267189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:53.267189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TamilEmo: Finegrained Emotion Detection Dataset for Tamil","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anbukkarasi Sampath, Bharathi Raja Chakravarthi, Charangan Vasantharajan, John Phillip McCrae, Kanchana Sivanraju, Prasanna Kumar Kumarasen, Rahul Ponnusamy, Ruba Priyadharshini, Sathiyaraj Thangasamy, Sean Benhur, Thenmozhi Durairaj","submitted_at":"2022-02-09T21:05:28Z","abstract_excerpt":"Emotional Analysis from textual input has been considered both a challenging and interesting task in Natural Language Processing. However, due to the lack of datasets in low-resource languages (i.e. Tamil), it is difficult to conduct research of high standard in this area. Therefore we introduce this labelled dataset (a largest manually annotated dataset of more than 42k Tamil YouTube comments, labelled for 31 emotions including neutral) for emotion recognition. The goal of this dataset is to improve emotion detection in multiple downstream tasks in Tamil. We have also created three different "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04725","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.04725/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":"2202.04725","created_at":"2026-07-05T03:55:53.267248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.04725v1","created_at":"2026-07-05T03:55:53.267248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04725","created_at":"2026-07-05T03:55:53.267248+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KCTUIO3HFY5","created_at":"2026-07-05T03:55:53.267248+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KCTUIO3HFY5CCD5","created_at":"2026-07-05T03:55:53.267248+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KCTUIO3","created_at":"2026-07-05T03:55:53.267248+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/3KCTUIO3HFY5CCD5QIL4GQSOWC","json":"https://pith.science/pith/3KCTUIO3HFY5CCD5QIL4GQSOWC.json","graph_json":"https://pith.science/api/pith-number/3KCTUIO3HFY5CCD5QIL4GQSOWC/graph.json","events_json":"https://pith.science/api/pith-number/3KCTUIO3HFY5CCD5QIL4GQSOWC/events.json","paper":"https://pith.science/paper/3KCTUIO3"},"agent_actions":{"view_html":"https://pith.science/pith/3KCTUIO3HFY5CCD5QIL4GQSOWC","download_json":"https://pith.science/pith/3KCTUIO3HFY5CCD5QIL4GQSOWC.json","view_paper":"https://pith.science/paper/3KCTUIO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.04725&json=true","fetch_graph":"https://pith.science/api/pith-number/3KCTUIO3HFY5CCD5QIL4GQSOWC/graph.json","fetch_events":"https://pith.science/api/pith-number/3KCTUIO3HFY5CCD5QIL4GQSOWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KCTUIO3HFY5CCD5QIL4GQSOWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KCTUIO3HFY5CCD5QIL4GQSOWC/action/storage_attestation","attest_author":"https://pith.science/pith/3KCTUIO3HFY5CCD5QIL4GQSOWC/action/author_attestation","sign_citation":"https://pith.science/pith/3KCTUIO3HFY5CCD5QIL4GQSOWC/action/citation_signature","submit_replication":"https://pith.science/pith/3KCTUIO3HFY5CCD5QIL4GQSOWC/action/replication_record"}},"created_at":"2026-07-05T03:55:53.267248+00:00","updated_at":"2026-07-05T03:55:53.267248+00:00"}