{"paper":{"title":"BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abu Raihan Mostofa Kamal, Md Azam Hossain, Md Farhan Ishmam, Md Shahnewaz Siddique, Navid Hasin Alvee, Sadia Alam","submitted_at":"2024-08-16T18:30:22Z","abstract_excerpt":"The widespread availability of code-mixed data can provide valuable insights into low-resource languages like Bengali, which have limited datasets. Sentiment analysis has been a fundamental text classification task across several languages for code-mixed data. However, there has yet to be a large-scale and diverse sentiment analysis dataset on code-mixed Bengali. We address this limitation by introducing BnSentMix, a sentiment analysis dataset on code-mixed Bengali consisting of 20,000 samples with 4 sentiment labels from Facebook, YouTube, and e-commerce sites. We ensure diversity in data sou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08964","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/2408.08964/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"}