A Comparative Analysis of Machine Learning Algorithms for Opinion Extraction from Web Text Using AI

Authors: Erugu Krishna, Vijay Ramnath Sonawane

Full-text Research PDF File:   View   |   Download

Abstract: The exponential growth of social media and online platforms has led to an enormous volume of user-generated web text, making automated opinion extraction an essential task for organizations and researchers. Sentiment analysis and opinion mining aim to identify users’ opinions, emotions, and attitudes from textual data to support decision-making processes. This study presents a comparative analysis of various machine learning algorithms for opinion extraction from web text using artificial intelligence techniques. The analysis focuses on feature-based and aspect-based sentiment analysis approaches applied to data such as product reviews, tourist reviews, social media comments, and e-commerce feedback. Traditional machine learning models including Support Vector Machine, Naive Bayes, K-Nearest Neighbor, and fuzzy-based frameworks are examined in terms of performance, advantages, and limitations. The findings highlight that while many models achieve high accuracy in domain-specific settings, challenges such as implicit aspect detection, domain dependency, and scalability remain unresolved. This work identifies research gaps and provides insights for developing more robust and generalizable AI-based opinion extraction systems.

Keywords: Sentiment Analysis, Opinion Mining, Machine Learning, Aspect-Based Sentiment Analysis, Web Text, Artificial Intelligence

Paper Id: 5.510

Published On: 2024-07-07

Published In: Special Issue - International Conference on Trends and Innovations in Management, Engineering, Sciences and Humanities (July 2024)

Share this