International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 186 - Number 26 |
Year of Publication: 2024 |
Authors: Nida Shaikh, A.S. Vaidya, D.V. Patil |
![]() |
Nida Shaikh, A.S. Vaidya, D.V. Patil . Prediction of Indian Election using sentiment analysis on Twitter (X) data: Review. International Journal of Computer Applications. 186, 26 ( Jul 2024), 18-22. DOI=10.5120/ijca2024923717
In recent years, social media platforms have emerged as powerful tools for understanding public opinion and sentiment towards various socio-political events, including elections. With the rise of Twitter as a prominent platform for political discourse, researchers have increasingly turned to sentiment analysis techniques to predict election outcomes. This review paper examines the state-of-the-art methods and findings in predicting Indian election results using sentiment analysis on Twitter data. The Paper commences with an introduction to the importance of sentiment analysis in political prediction, highlighting the distinctive hurdles presented by the Indian political terrain, known for its diversity, intricacy, and vastness. It then delves into the methodologies employed in sentiment analysis, ranging from lexicon-based approaches to machine learning techniques. The review highlights the advantages and limitations of each method and discusses their applicability to the Indian context. the paper critically evaluates existing studies that have applied sentiment analysis to Indian election data, focusing on their methodologies, datasets, and predictive accuracy. It examines the factors influencing sentiment polarity on Twitter, such as linguistic variations, regional sentiments, and the influence of political events and personalities. Additionally, the review discusses the ethical considerations and challenges associated with sentiment analysis in the context of political elections, including bias, privacy concerns, and the need for transparency. the paper identifies gaps in current research and suggests directions for future studies, such as exploring hybrid approaches combining opinion mining with other data sources, incorporating temporal dynamics into predictive models, and addressing the issue of data veracity and authenticity. Overall, this review provides valuable insights into the potential and limitations of sentiment analysis for predicting Indian election outcomes and offers guidance for researchers and learners in the field.