A Hybrid Lexicon–Transformer Framework for Sentiment, Emotion, and Context Classification in Moroccan Darija (TriLex-Darija)
ACM Transactions on Asian and Low-Resource Language Information Processing · 31.07.2026 · 25 (7) · 1-24
DOI: 10.1145/3812654 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 22.06.2026. Verfasst von Sara El Ouahabi und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This article introduces TriLex-Darija , a large-scale affective lexicon suite and a hybrid lexicon–transformer framework for analyzing Moroccan Arabic (Darija) social media text across three complementary dimensions: sentiment, emotion, and pragmatic context. The resource is constructed from a corpus of 288,709 manually annotated comments and consists of three unigram lexicons, each mapping 147,565 words to normalized probability distributions over task-specific labels. We first evaluate a symbolic lexicon-based classifier (without machine learning) based on word-level score aggregation to assess the intrinsic quality of the proposed TriLex-Darija resource. Despite the absence of contextual modeling, this approach achieves competitive performance, demonstrating that corpus-derived lexical knowledge captures substantial affective information in Moroccan Darija. To further improve performance, we propose a unified hybrid framework that combines TriLex-Darija features with contextual embeddings extracted from MARBERT. All models are trained using a consistent LinearSVC classifier to ensure fair comparison and reproducibility. In addition to the symbolic model, we evaluate a lexicon-feature-based LinearSVC model, allowing a clear distinction between symbolic, feature-based, and hybrid approaches. Experimental results show that the hybrid model consistently outperforms both BERT-only and lexicon-feature-based baselines across all tasks. For sentiment classification, the hybrid model achieves a macro F1-score of 72.96% , compared to 59.15% for BERT-only and 67.94% for the lexicon-feature-based model. For emotion classification, it reaches 92.92% , outperforming BERT-only ( 79.17% ) and lexicon-feature-based ( 89.55% ) models. For pragmatic context classification, the hybrid model achieves 91.35% , compared to 75.93% for BERT-only and 87.72% for the lexicon-feature-based model. Bootstrap confidence intervals (95%) and McNemar’s tests confirm that all improvements are statistically significant ( p < 0.001). Overall, TriLex-Darija demonstrates that combining lexical knowledge with contextual embeddings leads to robust, interpretable, and statistically validated affective models for Moroccan Darija in low-resource settings.
Zitieren
APA
Ouahabi, S. E., Ouahabi, S. E., & Dadi, E. W. (2026). A Hybrid Lexicon–Transformer Framework for Sentiment, Emotion, and Context Classification in Moroccan Darija (TriLex-Darija). ACM Transactions on Asian and Low-Resource Language Information Processing, 25(7), 1-24. https://doi.org/10.1145/3812654
Vancouver
Ouahabi SE, Ouahabi SE, Dadi EW. A Hybrid Lexicon–Transformer Framework for Sentiment, Emotion, and Context Classification in Moroccan Darija (TriLex-Darija). ACM Transactions on Asian and Low-Resource Language Information Processing. 2026;25(7):1-24. doi:10.1145/3812654
BibTeX
@article{Ouahabi2026,
author = {Ouahabi, Sara El and Ouahabi, Safâa El and Dadi, El Wardani},
title = {A Hybrid Lexicon–Transformer Framework for Sentiment, Emotion, and Context Classification in Moroccan Darija (TriLex-Darija)},
journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
year = {2026},
volume = {25},
number = {7},
pages = {1--24},
doi = {10.1145/3812654}
}
EUVIMED