An Empirical Analysis of Twitter Reviews Using Optimal Machine Learning Techniques
Rohini G. Khalkar, Mrunal S. Bewoor, Sampat P. Medhane · Engineering Technology & Applied Science Research · 2025
Sentiment analysis, a key method in Natural Language Processing (NLP), is used to recognize, extract, and classify subjective material from textual data. With the rapid development of user-generated content on social media platforms, such as Twitter, Facebook, and Instagram, sentiment analysis has gained significant importance. Social media platforms have proven to be useful for gauging customer reviews and brand perception to determine sentiments and thoughts on a variety of topics. Analyzing such data presents challenges due to the brevity of posts, informal syntax, slang, and the heavy use of emojis. This paper proposes a hybrid sentiment analysis framework that integrates textual features with emoji-based sentiment cues. A Support Vector Machine (SVM) classifier is employed along with a balancing factor to ensure vigorous classification. Support Vector Machine (SVM) is the most accurate approach for sentiment classification. Tailored preprocessing significantly improves classification accuracy by comparing traditional and Twitter-specific preprocessing methods. Feature extraction is carried out using Term Frequency-Inverse Document Frequency (TF-IDF), which captures the contextual importance of words. In addition, emoji sentiment mapping assigns predefined sentiment scores to frequently used emojis, thereby enhancing semantic understanding and enlightening the accuracy of sentiment predictions. This study demonstrates that it is important to select appropriate preprocessing and classification techniques for accurate sentiment analysis in a social media context. SVM, Logistic Regression (LR), and Naïve Bayes (NB) classifiers were applied on the sentiment140 dataset, focusing on a sentiment analysis of more than 1.5 million tweets. SVM was found to be more effective when working with a balancing factor that considers the standard deviation.