{"paper":{"title":"MaCmS: Magahi Code-mixed Dataset for Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaurav Negi, John P. McCrae, Priya Rani, Theodorus Fransen","submitted_at":"2024-03-07T16:29:19Z","abstract_excerpt":"The present paper introduces new sentiment data, MaCMS, for Magahi-Hindi-English (MHE) code-mixed language, where Magahi is a less-resourced minority language. This dataset is the first Magahi-Hindi-English code-mixed dataset for sentiment analysis tasks. Further, we also provide a linguistics analysis of the dataset to understand the structure of code-mixing and a statistical study to understand the language preferences of speakers with different polarities. With these analyses, we also train baseline models to evaluate the dataset's quality."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04639","kind":"arxiv","version":2},"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/2403.04639/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"}