Scholarlink

This research investigates multilingual sentiment analysis through the lens of a hybrid deep learning model, combining Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU). Our study encompasses datasets in English, Portuguese, Tamil, and French, sourced from diverse online platforms and encompassing various sentiment labels. Methodologically, we detail data collection, preprocessing tailored to each language, model architecture, training techniques, and performance evaluation metrics. Results indicate superior performance of our proposed model across all languages, surpassing established benchmarks in terms of F1 score, recall, precision, and accuracy. Visual representations including confusion matrices and ROC curves further elucidate the model’s efficacy. This study underscores the significance of hybrid deep learning approaches in advancing multilingual sentiment analysis, offering insights for future research and practical applications in natural language processing.

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

Enhanced Multilingual Sentiment Analysis Using Hybrid CNN-GRU Deep Learning Architecture

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Vipin Jain,
  • Garima Mohanani,
  • Arpit Gaur,
  • Pushpinder Singh Patheja

摘要

This research investigates multilingual sentiment analysis through the lens of a hybrid deep learning model, combining Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU). Our study encompasses datasets in English, Portuguese, Tamil, and French, sourced from diverse online platforms and encompassing various sentiment labels. Methodologically, we detail data collection, preprocessing tailored to each language, model architecture, training techniques, and performance evaluation metrics. Results indicate superior performance of our proposed model across all languages, surpassing established benchmarks in terms of F1 score, recall, precision, and accuracy. Visual representations including confusion matrices and ROC curves further elucidate the model’s efficacy. This study underscores the significance of hybrid deep learning approaches in advancing multilingual sentiment analysis, offering insights for future research and practical applications in natural language processing.