Hybrid XLM-R + Character-CNN Fusion for Robust Multilingual and Code-Mixed Sentiment Classification
Jurnal Multidisiplin Indonesia · 31.03.2025 · 3 (1) · 61-76
DOI: 10.62007/joumi.v3i1.673 ↗Kurz gefasst
Fachartikel in der Zeitschrift Jurnal Multidisiplin Indonesia, online erschienen am 31.03.2025. Verfasst von Danang Danang und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Multilingual and code-mixed user-generated text (UGT) is noisy: spelling variants, elongations, and typos are common and can degrade transformer-only sentiment classifiers. This paper evaluates a hybrid architecture that fuses a subword transformer encoder (XLM R) with a character-level convolutional branch (CharCNN) to improve robustness under character-level perturbations. We benchmark on two test settings: (1) NusaX, a multilingual Southeast-Asian sentiment dataset, and (2) Indonglish, an Indonesian–English code-mixed sentiment dataset. We report standard clean-set metrics (Accuracy, Macro-F1) and a controlled robustness protocol that applies character-level noise with probability p = 0.18 (seed = 42) and measures performance drops. Results show the hybrid model reduces robustness degradation substantially on code-mixed text (Macro-F1 drop 0.007 vs. 0.030 for the XLM-R baseline), while incurring a modest clean-set performance trade-off. We provide an end-to-end pipeline, ablation analysis, and reproducible reporting artifacts (metrics JSON, confusion matrices, and error samples).
Zitieren
APA
Danang, D., & Putra, T. W. A. (2025). Hybrid XLM-R + Character-CNN Fusion for Robust Multilingual and Code-Mixed Sentiment Classification. Jurnal Multidisiplin Indonesia, 3(1), 61-76. https://doi.org/10.62007/joumi.v3i1.673
Vancouver
Danang D, Putra TWA. Hybrid XLM-R + Character-CNN Fusion for Robust Multilingual and Code-Mixed Sentiment Classification. Jurnal Multidisiplin Indonesia. 2025;3(1):61-76. doi:10.62007/joumi.v3i1.673
BibTeX
@article{Danang2025,
author = {Danang, Danang and Putra, Toni Wijanarko Adi},
title = {Hybrid XLM-R + Character-CNN Fusion for Robust Multilingual and Code-Mixed Sentiment Classification},
journal = {Jurnal Multidisiplin Indonesia},
year = {2025},
volume = {3},
number = {1},
pages = {61--76},
doi = {10.62007/joumi.v3i1.673}
}
EUVIMED