Scholarlink

<p>Multilingual language models achieve strong results in emotion classification; however, their robustness under culturally complex and linguistically diverse conditions remains limited. Standard evaluations rely on structured datasets that do not capture phenomena such as code-switching, idiomatic expressions, and indirect affective language, which are common in real-world communication. This study introduces a culturally oriented evaluation framework to analyze the behavior of mBERT, XLM-R, and a fine-tuned variant (XLM-R-FT) under non-standard linguistic conditions. The evaluation combines a multilingual dataset with a subset of manually annotated samples incorporating regional variation in Spanish, Portuguese, and Italian. Results show consistent performance degradation on culturally marked inputs, with reductions of up to 10 F1 points. Fine-tuning improves stability but does not eliminate sensitivity to implicit and idiomatic expressions. Interpretability analysis using LIME and SHAP indicates that predictions are often driven by lexically salient tokens, leading to misinterpretations. The proposed framework enables evaluation beyond standard benchmarks and highlights the need to incorporate cultural and linguistic variability in multilingual emotion analysis.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multilingual Evaluation of Semantic Robustness and Cultural Adaptability in Transformer Models for Emotion Recognition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月30日

查看全文
  • William Villegas-Ch,
  • Rommel Gutierrez,
  • Aracely Mera-Navarrete,
  • Rodrigo Guevara-Reyes

摘要

Multilingual language models achieve strong results in emotion classification; however, their robustness under culturally complex and linguistically diverse conditions remains limited. Standard evaluations rely on structured datasets that do not capture phenomena such as code-switching, idiomatic expressions, and indirect affective language, which are common in real-world communication. This study introduces a culturally oriented evaluation framework to analyze the behavior of mBERT, XLM-R, and a fine-tuned variant (XLM-R-FT) under non-standard linguistic conditions. The evaluation combines a multilingual dataset with a subset of manually annotated samples incorporating regional variation in Spanish, Portuguese, and Italian. Results show consistent performance degradation on culturally marked inputs, with reductions of up to 10 F1 points. Fine-tuning improves stability but does not eliminate sensitivity to implicit and idiomatic expressions. Interpretability analysis using LIME and SHAP indicates that predictions are often driven by lexically salient tokens, leading to misinterpretations. The proposed framework enables evaluation beyond standard benchmarks and highlights the need to incorporate cultural and linguistic variability in multilingual emotion analysis.