Scholarlink

<p>Deep learning (DL), when integrated with nature inspired optimization techniques, has emerged as a crucial approach for enhancing multi class sentiment analysis (MSA) in text data. This study introduces an innovative framework for the sentiment classification of movie reviews, leveraging a metaheuristic Bidirectional Gated Recurrent Unit (Bi-GRU) model. Our methodology starts by pre-processing using Natural Language Toolkit (NLTK), and extracting distinctive feature polarity, and then feed these score into a Bi-GRU. Furthermore, we address the optimization of our Bi-GRU model using Octopus Swarm Optimization (OSO) algorithm. Our experiment reveals that optimization of the Bi-GRU with OSO yields a significantly improve the model performance, further validating the efficacy of our classification framework. This paper illustrates how the combination of deep learning and intelligent optimization algorithms can significantly improve the accuracy of natural language processing tasks, such as sentiment 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

Bi-GRU-OSO: a novel framework for enhanced multiclass sentiment analysis using Bi-GRU networks optimized with octopus swarm optimization

  • 期刊论文

  • 发表日期：

    2025年12月1日

查看全文
  • Amit Kumar Srivastava,
  • Pooja,
  • T. J. Siddiqui,
  • Anima Srivastava

摘要

Deep learning (DL), when integrated with nature inspired optimization techniques, has emerged as a crucial approach for enhancing multi class sentiment analysis (MSA) in text data. This study introduces an innovative framework for the sentiment classification of movie reviews, leveraging a metaheuristic Bidirectional Gated Recurrent Unit (Bi-GRU) model. Our methodology starts by pre-processing using Natural Language Toolkit (NLTK), and extracting distinctive feature polarity, and then feed these score into a Bi-GRU. Furthermore, we address the optimization of our Bi-GRU model using Octopus Swarm Optimization (OSO) algorithm. Our experiment reveals that optimization of the Bi-GRU with OSO yields a significantly improve the model performance, further validating the efficacy of our classification framework. This paper illustrates how the combination of deep learning and intelligent optimization algorithms can significantly improve the accuracy of natural language processing tasks, such as sentiment analysis.