Paper Contents
Abstract
In the digital age, election campaigns have increasingly migrated to online platforms, where voter sentiments are continuously shaped by social media and digital interactions. This paper explores how machine learning (ML) techniques can be leveraged to analyze and interpret voter sentiment during Member of Parliament (MP) elections. By utilizing natural language processing (NLP), sentiment analysis, and predictive modeling, this study aims to provide insights into public opinion dynamics and their influence on electoral outcomes. Our research spans a six-month period leading up to the MP elections, analyzing over 3 million social media posts across multiple platforms. The study achieved an average sentiment classification accuracy of 83% and demonstrated significant correlations between online sentiment patterns and electoral outcomes. Additionally, we discuss the challenges and ethical considerations associated with AI-driven sentiment analysis in the political landscape, including issues of privacy, bias, and the impact of misinformation campaigns. The findings suggest that while ML-based sentiment analysis can be a powerful tool for understanding voter behavior, careful consideration must be given to its limitations and potential societal implications.
Copyright
Copyright © 2025 Pavan Kumar Goyal, Dr. Prashant Sen, Dr.Anil Pimplapure. This is an open access article distributed under the Creative Commons Attribution License.
