{"paper":{"title":"RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RoIt-XMASA dataset with meta-learned adversarial training lets XLM-R reach 66.23% F1 in cross-lingual and cross-domain sentiment analysis for Italian and Romanian.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei-Marius Avram, Aureliu Valentin Antonie, Cosmin-Mircea Croitoru, Dumitru-Clementin Cercel, Vlad Andrei Muntean","submitted_at":"2026-04-18T20:21:40Z","abstract_excerpt":"We present RoIt-XMASA, a multilingual dataset that extends the Cross-lingual Multi-domain Amazon Sentiment Analysis to Italian and Romanian, comprising 36,000 labeled reviews across three domains (books, movies, and music) and 202,141 unlabeled samples. To address cross-lingual and cross-domain challenges, we propose a multi-target adversarial training framework that employs loss reversal with meta-learned coefficients to dynamically balance sentiment discrimination with domain and language invariance. XLM-R achieves an F1-score of 66.23% with our approach, outperforming the baseline by 4.64%."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"XLM-R achieves an F1-score of 66.23% with our approach, outperforming the baseline by 4.64%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The meta-learned coefficients successfully balance sentiment discrimination against domain and language invariance without causing training instability or overfitting on the specific dataset splits.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"New dataset for Romanian and Italian multi-domain sentiment analysis combined with an adversarial framework that improves XLM-R F1 by 4.64% over baseline.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RoIt-XMASA dataset with meta-learned adversarial training lets XLM-R reach 66.23% F1 in cross-lingual and cross-domain sentiment analysis for Italian and Romanian.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7742646e7a7d307326cb3748975d65fda3d47c5594569dfe6e469a8c9ba9141f"},"source":{"id":"2604.17134","kind":"arxiv","version":2},"verdict":{"id":"ccf97bba-ccc0-4934-b37d-c4bedc1c256b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T06:24:26.488092Z","strongest_claim":"XLM-R achieves an F1-score of 66.23% with our approach, outperforming the baseline by 4.64%.","one_line_summary":"New dataset for Romanian and Italian multi-domain sentiment analysis combined with an adversarial framework that improves XLM-R F1 by 4.64% over baseline.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The meta-learned coefficients successfully balance sentiment discrimination against domain and language invariance without causing training instability or overfitting on the specific dataset splits.","pith_extraction_headline":"RoIt-XMASA dataset with meta-learned adversarial training lets XLM-R reach 66.23% F1 in cross-lingual and cross-domain sentiment analysis for Italian and Romanian."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17134/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"}