Machine Learning and Sentiment Detection: a Comparative Classifier Study
Year: 2026
Type: article
Abstract: Sentiment detection has become a crucial application in natural language processing (NLP), widely used in areas such as social media monitoring, product reviews, and customer feedback analysis. Machine learning (ML) classifiers play a pivotal role in determining sentiment polarity (positive, negative, or neutral) with varying degrees of accuracy and efficiency. This study provides a comparative analysis of different ML classifiers used for sentiment detection, including Naïve Bayes, Support Vector Machines (SVM), Decision Trees, Random Forest, and deep learning-based approaches like Long Short-Term Memory (LSTM) networks and Bidirectional Encoder Representations from Transformers (BERT). The evaluation is conducted using benchmark datasets such as IMDb, Yelp, and Twitter sentiment datasets. Performance metrics like accuracy, precision, recall, and F1-score are used to determine the most effective classifier for sentiment analysis tasks. The study provides insights into the advantages and limitations of each classifier and suggests optimal models for different sentiment detection applications.
Authors: Radha Raman Chaurasiya, Dr. Ramveer Singh
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7215801873