{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N43HAGTNCBPHT2KFAZHI5FAQSR","short_pith_number":"pith:N43HAGTN","schema_version":"1.0","canonical_sha256":"6f36701a6d105e79e945064e8e9410947186d2ca818d613e8954af8d48ed7cd5","source":{"kind":"arxiv","id":"2502.06180","version":1},"attestation_state":"computed","paper":{"title":"RideKE: Leveraging Low-Resource, User-Generated Twitter Content for Sentiment and Emotion Detection in Kenyan Code-Switched Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Maria L. Gini, Naome A. Etori","submitted_at":"2025-02-10T06:18:07Z","abstract_excerpt":"Social media has become a crucial open-access platform for individuals to express opinions and share experiences. However, leveraging low-resource language data from Twitter is challenging due to scarce, poor-quality content and the major variations in language use, such as slang and code-switching. Identifying tweets in these languages can be difficult as Twitter primarily supports high-resource languages. We analyze Kenyan code-switched data and evaluate four state-of-the-art (SOTA) transformer-based pretrained models for sentiment and emotion classification, using supervised and semi-superv"},"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":"2502.06180","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T06:18:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"47aa3e4c338fbc18a208f2e3a9e6636d4885ef9d8c56e9b992a0c37abb957862","abstract_canon_sha256":"a4bbd88f36e02e54955f634961e42160f2e3a4db33849666d5d560ffef72bd63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:48.737902Z","signature_b64":"f47zst7+v0R+UpnWDO6KPF1GwVuJ9gsEkL9rS89dJKvhv14t/iIwISx0uu8iWU51S8K6U6ZnXoUk7SDHwCJrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f36701a6d105e79e945064e8e9410947186d2ca818d613e8954af8d48ed7cd5","last_reissued_at":"2026-07-05T10:11:48.737323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:48.737323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RideKE: Leveraging Low-Resource, User-Generated Twitter Content for Sentiment and Emotion Detection in Kenyan Code-Switched Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Maria L. Gini, Naome A. Etori","submitted_at":"2025-02-10T06:18:07Z","abstract_excerpt":"Social media has become a crucial open-access platform for individuals to express opinions and share experiences. However, leveraging low-resource language data from Twitter is challenging due to scarce, poor-quality content and the major variations in language use, such as slang and code-switching. Identifying tweets in these languages can be difficult as Twitter primarily supports high-resource languages. We analyze Kenyan code-switched data and evaluate four state-of-the-art (SOTA) transformer-based pretrained models for sentiment and emotion classification, using supervised and semi-superv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06180","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/2502.06180/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":"2502.06180","created_at":"2026-07-05T10:11:48.737393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06180v1","created_at":"2026-07-05T10:11:48.737393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06180","created_at":"2026-07-05T10:11:48.737393+00:00"},{"alias_kind":"pith_short_12","alias_value":"N43HAGTNCBPH","created_at":"2026-07-05T10:11:48.737393+00:00"},{"alias_kind":"pith_short_16","alias_value":"N43HAGTNCBPHT2KF","created_at":"2026-07-05T10:11:48.737393+00:00"},{"alias_kind":"pith_short_8","alias_value":"N43HAGTN","created_at":"2026-07-05T10:11:48.737393+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/N43HAGTNCBPHT2KFAZHI5FAQSR","json":"https://pith.science/pith/N43HAGTNCBPHT2KFAZHI5FAQSR.json","graph_json":"https://pith.science/api/pith-number/N43HAGTNCBPHT2KFAZHI5FAQSR/graph.json","events_json":"https://pith.science/api/pith-number/N43HAGTNCBPHT2KFAZHI5FAQSR/events.json","paper":"https://pith.science/paper/N43HAGTN"},"agent_actions":{"view_html":"https://pith.science/pith/N43HAGTNCBPHT2KFAZHI5FAQSR","download_json":"https://pith.science/pith/N43HAGTNCBPHT2KFAZHI5FAQSR.json","view_paper":"https://pith.science/paper/N43HAGTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06180&json=true","fetch_graph":"https://pith.science/api/pith-number/N43HAGTNCBPHT2KFAZHI5FAQSR/graph.json","fetch_events":"https://pith.science/api/pith-number/N43HAGTNCBPHT2KFAZHI5FAQSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N43HAGTNCBPHT2KFAZHI5FAQSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N43HAGTNCBPHT2KFAZHI5FAQSR/action/storage_attestation","attest_author":"https://pith.science/pith/N43HAGTNCBPHT2KFAZHI5FAQSR/action/author_attestation","sign_citation":"https://pith.science/pith/N43HAGTNCBPHT2KFAZHI5FAQSR/action/citation_signature","submit_replication":"https://pith.science/pith/N43HAGTNCBPHT2KFAZHI5FAQSR/action/replication_record"}},"created_at":"2026-07-05T10:11:48.737393+00:00","updated_at":"2026-07-05T10:11:48.737393+00:00"}