HCASO: Hybrid Cross-Lingual Attention with Contrastive Alignment and Optimized Lexical Fusion for Bilingual E-Commerce Sentiment Analysis
Complex Systems Informatics and Modeling Quarterly · 31.10.2026 · (48) · 52-75
DOI: 10.7250/csimq.2026-48.03 ↗Kurz gefasst
Fachartikel in der Zeitschrift Complex Systems Informatics and Modeling Quarterly, online erschienen am 31.10.2026. Verfasst von Himaani Srivatsava und 1 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Shared-encoder multilingual models that confound typologically different language representations scarcely support cross-lingual sentiment analysis. This article introduces HCASO (Hybrid Cross-Lingual Attention with Contrastive Alignment and Optimized Lexical Fusion for Sentiment Analysis) as a unified bilingual model, which consists of four elements: (i) language-specific English and Chinese ELECTRA encoders, (ii) cross-lingual attention that allows structured inter-language communication, (iii) a symmetric InfoNCE contrastive loss in a 256-dimensional space that allows the languages to achieve clearer alignment, and (iv) a two-stage gated lexical fusion module that adaptively combines TF-IDF and sentiment lexicon features with contextual encoder representations via a learned per-dimension mixing coefficient. The model is trained using cross-entropy, MSE intensity regression, and the contrastive objectives. Post-hoc temperature scaling was used to calibrate it. Compared to standard baselines, HCASO achieves the strongest overall balance of performance, with ROC-AUC of 0.9361, 0.8623, and 0.8474 on binary, ternary, and quinary MARC English-Chinese sentiment classification, respectively. HCASO performs best on ordinal consistency (MSE = 0.0455, R² = 0.6356, Top-2 = 0.8211) across settings, with XLM-RoBERTa-Base being slightly more accurate in terms of raw accuracy in quinary classification. Ablation experiments with McNemar tests confirmed that all the components - dual encoders (p < 10⁻²⁶ across all settings), lexical fusion (p < 10⁻¹¹ in the ternary setting), and contrastive alignment (p = 0.028 in the quinary setting) each contribute significantly. HCASO is a statistically validated alternative to the shared-encoder paradigm, which scales at 214.4M parameters and 10.89 GMACs.
Zitieren
APA
Srivatsava, H., & Ganesan, G. (2026). HCASO: Hybrid Cross-Lingual Attention with Contrastive Alignment and Optimized Lexical Fusion for Bilingual E-Commerce Sentiment Analysis. Complex Systems Informatics and Modeling Quarterly, 52-75. https://doi.org/10.7250/csimq.2026-48.03
Vancouver
Srivatsava H, Ganesan G. HCASO: Hybrid Cross-Lingual Attention with Contrastive Alignment and Optimized Lexical Fusion for Bilingual E-Commerce Sentiment Analysis. Complex Systems Informatics and Modeling Quarterly. 2026:52-75. doi:10.7250/csimq.2026-48.03
BibTeX
@article{Srivatsava2026,
author = {Srivatsava, Himaani and Ganesan, Gangadevi},
title = {HCASO: Hybrid Cross-Lingual Attention with Contrastive Alignment and Optimized Lexical Fusion for Bilingual E-Commerce Sentiment Analysis},
journal = {Complex Systems Informatics and Modeling Quarterly},
year = {2026},
number = {48},
pages = {52--75},
doi = {10.7250/csimq.2026-48.03}
}
EUVIMED