Sentiment analysis using support vector machines techniques on Twitter data
Shamy Ahmad, Manish Kumar, Sachin Bhardwaj · Computational Methods in Science and Technology · 2024
Understanding and extracting emotions from textual content requires a special branch of natural language processing called emotion analysis. Because of its ability to handle high-dimensional data and nonlinear combinations, support vector machines (SVM) have emerged as one of the most powerful techniques in sentiment analysis In this paper sentiment polarity i.e. sentiment analysis using SVM techniques to determine whether sentiment is positive, negative or neutral Overview The review presented covers the theoretical foundations of SVM, its application in sentiment analysis, and several extraction methods a it contains and represents. It also looks at sensitivity analysis challenges, such as sparse data and class imbalances, and how SVM methods address these issues. Several case studies and applications of SVM in sentiment analysis in various industries—such as social media, product reviews, and customer feedback—have been proposed to illustrate how methods stand SVM over is effective and versatile Highlights the importance of continuous improvements in machine learning algorithms and information processing techniques In conclusion, this work provides a comprehensive understanding of sensitivity analysis using SVM techniques are used, sensitivity analysis to extract meaningful information from textual data for business intelligence and decision-making needs It demonstrates its importance.