BDSI at AraSentEval Shared Task : A Multi-Transformer Contrastive Learning for Arabic Dialect Sentiment Analysis

Mohamed M’haouach, Kaouthar Elyoussoufi, Abdessamad Benlahbib, Hamza Alami


Abstract
This paper presents our system for the AraSentEval 2026 shared task on Arabic dialect sentiment analysis. We propose a multi-model ensemble combining AraBERTv2 and CAMeLBERT with supervised contrastive learning to improve sentiment classification. The system incorporates dialect-aware preprocessing, class-weighted cross-entropy loss with label smoothing, supervised contrastive loss for enhanced sentence representations, and rule-based post-processing for dialect-specific patterns. Our approach achieves a macro F1-score of 0.83 on the official test set, demonstrating the effectiveness of contrastive learning with pretrained Arabic language models for dialectal sentiment analysis.
Anthology ID:
2026.osact-1.39
Volume:
The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Hend Al-Khalifa, Mo El-Haj, Saad Ezzini
Venues:
OSACT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
284–287
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-osact-39
DOI:
10.63317/4prectoefpgj
Bibkey:
Cite (ACL):
Mohamed M’haouach, Kaouthar Elyoussoufi, Abdessamad Benlahbib, and Hamza Alami. 2026. BDSI at AraSentEval Shared Task : A Multi-Transformer Contrastive Learning for Arabic Dialect Sentiment Analysis. In The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks, pages 284–287, Palma, Mallorca (Spain). Association for Computational Linguistics.
Cite (Informal):
BDSI at AraSentEval Shared Task : A Multi-Transformer Contrastive Learning for Arabic Dialect Sentiment Analysis (M’haouach et al., OSACT 2026)
Copy Citation: