{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VUSHCIXGYSH5EAE5HW4Q5WCZML","short_pith_number":"pith:VUSHCIXG","schema_version":"1.0","canonical_sha256":"ad247122e6c48fd2009d3db90ed85962c5a9b2993158a30966085bc01aacc7c9","source":{"kind":"arxiv","id":"2504.13545","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"A.M.N.H. Adhikari, Azmarah Rizvi, Dharshana Kasthurirathna, Lakmini Abeywardhana, Navojith Thamindu, W.P.U. Senevirathna","submitted_at":"2025-04-18T08:21:12Z","abstract_excerpt":"Sentiment analysis is crucial for brand reputation management in the banking sector, where customer feedback spans English, Sinhala, Singlish, and code-mixed text. Existing models struggle with low-resource languages like Sinhala and lack interpretability for practical use. This research develops a hybrid aspect-based sentiment analysis framework that enhances multilingual capabilities with explainable outputs. Using cleaned banking customer reviews, we fine-tune XLM-RoBERTa for Sinhala and code-mixed text, integrate domain-specific lexicon correction, and employ BERT-base-uncased for English."},"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":"2504.13545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T08:21:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e331354e01440b50a8cf564fa259fc1c735164eafb1e8f69d484b221e524c245","abstract_canon_sha256":"2075e80baf7f159b84c5128140be281cf6b92a87054139386081175139e004df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:57.461706Z","signature_b64":"jys4244Lvtggr/sMsJH+HQmjAipaAI9bSaxk4LmpSVOykoU8gMs/ngz5qrNDC81TcJDWdL2oRqmUFDgjhViWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad247122e6c48fd2009d3db90ed85962c5a9b2993158a30966085bc01aacc7c9","last_reissued_at":"2026-07-05T10:50:57.461201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:57.461201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Multilingual Sentiment Analysis with Explainability for Sinhala, English, and Code-Mixed Content","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"A.M.N.H. Adhikari, Azmarah Rizvi, Dharshana Kasthurirathna, Lakmini Abeywardhana, Navojith Thamindu, W.P.U. Senevirathna","submitted_at":"2025-04-18T08:21:12Z","abstract_excerpt":"Sentiment analysis is crucial for brand reputation management in the banking sector, where customer feedback spans English, Sinhala, Singlish, and code-mixed text. Existing models struggle with low-resource languages like Sinhala and lack interpretability for practical use. This research develops a hybrid aspect-based sentiment analysis framework that enhances multilingual capabilities with explainable outputs. Using cleaned banking customer reviews, we fine-tune XLM-RoBERTa for Sinhala and code-mixed text, integrate domain-specific lexicon correction, and employ BERT-base-uncased for English."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13545","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/2504.13545/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":"2504.13545","created_at":"2026-07-05T10:50:57.461260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13545v1","created_at":"2026-07-05T10:50:57.461260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13545","created_at":"2026-07-05T10:50:57.461260+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUSHCIXGYSH5","created_at":"2026-07-05T10:50:57.461260+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUSHCIXGYSH5EAE5","created_at":"2026-07-05T10:50:57.461260+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUSHCIXG","created_at":"2026-07-05T10:50:57.461260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05259","citing_title":"SalAngaBhava: A Sinhala Market Dataset for Aspect-based Sentiment Analysis","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML","json":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML.json","graph_json":"https://pith.science/api/pith-number/VUSHCIXGYSH5EAE5HW4Q5WCZML/graph.json","events_json":"https://pith.science/api/pith-number/VUSHCIXGYSH5EAE5HW4Q5WCZML/events.json","paper":"https://pith.science/paper/VUSHCIXG"},"agent_actions":{"view_html":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML","download_json":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML.json","view_paper":"https://pith.science/paper/VUSHCIXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13545&json=true","fetch_graph":"https://pith.science/api/pith-number/VUSHCIXGYSH5EAE5HW4Q5WCZML/graph.json","fetch_events":"https://pith.science/api/pith-number/VUSHCIXGYSH5EAE5HW4Q5WCZML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML/action/storage_attestation","attest_author":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML/action/author_attestation","sign_citation":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML/action/citation_signature","submit_replication":"https://pith.science/pith/VUSHCIXGYSH5EAE5HW4Q5WCZML/action/replication_record"}},"created_at":"2026-07-05T10:50:57.461260+00:00","updated_at":"2026-07-05T10:50:57.461260+00:00"}