Parallel Text Classification Using Sentiment

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publicationRecent Trends in Artificial Intelligence and Data Sciences - Select Proceedings of the 15th International Conference, CONFLUENCE 2025
EditorsSumit Kumar, Garima Aggarwal, Bhuvan Unhelkar, Raju Pal
PublisherSpringer Science and Business Media Deutschland GmbH
Pages353-362
Number of pages10
ISBN (Print)9789819692026
DOIs
Publication statusPublished - 2025
Event15th International Conference on Recent Trends in Artificial Intelligence and Data Sciences, CONFLUENCE 2025 - New Delhi, India
Duration: 16-01-202517-01-2025

Publication series

NameLecture Notes in Electrical Engineering
Volume1447 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference15th International Conference on Recent Trends in Artificial Intelligence and Data Sciences, CONFLUENCE 2025
Country/TerritoryIndia
CityNew Delhi
Period16-01-2517-01-25

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Parallel Text Classification Using Sentiment'. Together they form a unique fingerprint.

Cite this