Mohammad Mozammal Huq, Jahangirnagar University, Bangladesh

This research study examines the efficacy of several machine learning models and techniques for sentiment analysis. The collected data and analysis provide valuable insights into sentiment analysis and its application to a large number of unlabeled consumer reviews and comments on Amazon products. The research study suggests a random forest model with a specific feature extraction technique to classify the sentiment of the reviews. The core theory of the model, analysis techniques, and performance standards are all covered in detail, along with a thorough overview of relevant literature on sentiment analysis using text-based datasets. Experiments on a small dataset produced encouraging results, with the random forest model achieving an accuracy of over 82 percent, and the classifier achieving a perfect AUC score of 1.00. The comparison of different methods, including cross-validation, varied training-testing ratios, and various feature extraction methods, contributed to the robustness of the findings.

Sentiment Analysis, Machine Learning, Text Classification, NLP, Random ForestModel