Scholarlink

<p>The exponential growth of online data presents significant challenges in effectively analyzing customer emotions, crucial for strategic business decision-making. This research introduces the Spider Wasp-Based Deep Neural Prediction Framework (SWDNPF), a novel approach to sentiment analysis and emotion prediction in large-scale datasets. Utilizing a comprehensive Flipkart product review dataset, SWDNPF combines advanced preprocessing, feature extraction, and sentiment analysis techniques to accurately predict customer emotions. The framework’s design optimizes the sentiment classification process by filtering noise, identifying key emotional attributes, and categorizing sentiments as positive, negative, or neutral. Extensive performance evaluations demonstrate SWDNPF's superiority over existing models, achieving an accuracy rate of 99.57%, alongside high precision, recall, and F-score metrics. The results underline the framework’s potential to enhance customer sentiment analysis, offering businesses deeper insights into consumer preferences and improving their responsiveness to market demands. Future work aims to extend SWDNPF’s application across multiple platforms and languages, further refining its capabilities and broadening its utility in global 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

A spider wasp-based deep neural prediction framework for emotion recognition and sentiment analysis in big data

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月13日

查看全文
  • Udayaraju Pamula,
  • G. N. V. G. Sirisha,
  • Ravi Babu Devareddi,
  • R. Sathish Kumar,
  • T. Santhi Sri,
  • Nanditha Boddu,
  • Ramesh Vatambeti

摘要

The exponential growth of online data presents significant challenges in effectively analyzing customer emotions, crucial for strategic business decision-making. This research introduces the Spider Wasp-Based Deep Neural Prediction Framework (SWDNPF), a novel approach to sentiment analysis and emotion prediction in large-scale datasets. Utilizing a comprehensive Flipkart product review dataset, SWDNPF combines advanced preprocessing, feature extraction, and sentiment analysis techniques to accurately predict customer emotions. The framework’s design optimizes the sentiment classification process by filtering noise, identifying key emotional attributes, and categorizing sentiments as positive, negative, or neutral. Extensive performance evaluations demonstrate SWDNPF's superiority over existing models, achieving an accuracy rate of 99.57%, alongside high precision, recall, and F-score metrics. The results underline the framework’s potential to enhance customer sentiment analysis, offering businesses deeper insights into consumer preferences and improving their responsiveness to market demands. Future work aims to extend SWDNPF’s application across multiple platforms and languages, further refining its capabilities and broadening its utility in global sentiment analysis.