Analyzing Machine Learning Approaches for Opinion Extraction from Web Text: Methods, Gaps, and Challenges

Authors: Erugu Krishna, Vijay Ramnath Sonawane

Full-text Research PDF File:   View   |   Download

Abstract: The rapid growth of Web 2.0 platforms has led to an unprecedented volume of user-generated content in the form of reviews, comments, blogs, and social media posts. Extracting opinions from such web text has become crucial for understanding public sentiment and supporting decision-making in business, governance, and social analysis. This paper analyzes machine learning approaches for opinion extraction from web text, focusing on commonly used methods, achieved results, existing gaps, and unresolved challenges. Traditional machine learning techniques such as Support Vector Machine, Naive Bayes, K-Nearest Neighbor, and hybrid frameworks are examined across multiple application domains, including e-commerce, transportation, media, and multilingual contexts. The analysis reveals that while high accuracy is often reported in domain-specific settings, limitations remain in handling implicit opinions, noisy web language, multilingual data, and cross-domain generalization. This study consolidates existing findings, highlights research gaps, and provides insights to guide future development of more robust and adaptable opinion extraction systems.

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

Paper Id: 5.512

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