Scholarlink

With the exponential growth of user-generated content on platforms like YouTube, efficient sentiment analysis methods are crucial for real-time insights into audience engagement and feedback. This paper uses the Naïve Bayes classifier combined with Message Passing Interface (MPI) and Compute Unified Device Architecture (CUDA) frameworks to analyse sentiment of YouTube comments in parallel. By distributing sentiment computation tasks across multiple processors and leveraging GPU capabilities, this method significantly reduces analysis time for large-scale datasets. The results show that while both MPI and CUDA provide significant speedup over sequential execution, CUDA outperforms MPI in terms of speedup metrics, offering superior performance for large-scale data. This demonstrates the effectiveness of parallel approach, highlighting substantial improvements in processing speed, thus offering a scalable solution for high-volume data analysis.

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

Parallel Text Classification Using Sentiment

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Aditya Basavaraj Halingali,
  • S. R. Ruchitha,
  • N. Gopalakrishna Kini,
  • K. Jyothi Upadhya

摘要

With the exponential growth of user-generated content on platforms like YouTube, efficient sentiment analysis methods are crucial for real-time insights into audience engagement and feedback. This paper uses the Naïve Bayes classifier combined with Message Passing Interface (MPI) and Compute Unified Device Architecture (CUDA) frameworks to analyse sentiment of YouTube comments in parallel. By distributing sentiment computation tasks across multiple processors and leveraging GPU capabilities, this method significantly reduces analysis time for large-scale datasets. The results show that while both MPI and CUDA provide significant speedup over sequential execution, CUDA outperforms MPI in terms of speedup metrics, offering superior performance for large-scale data. This demonstrates the effectiveness of parallel approach, highlighting substantial improvements in processing speed, thus offering a scalable solution for high-volume data analysis.