COMPARISON OF DIFFERENT CLASSIFICATION MODELSFOR SENTIMENT ANALYSIS

In this work, we explored sentiment analysis techniques oftexts using the example of product comments in the Kazakh language. To dothis, we used machine learning methods such as Naive Bayes, Random Forest,Logistic Regression and Support Vector Machine, as well as text processingtools: CountVectorizer and TfidfVectorizer. In the process of work,experiments were carried out with different configurations of models andparameters of vectorizers. To assess the quality of the models, we usedaccuracy, precision, recall and F1-score metrics. The research findingsindicated that the application of machine learning techniques make it possibleto achieve high accuracy in sentiment analysis of comments. The best resultswere obtained using the Support Vector Machine and TfidfVectorizer. Thisstudy can be used to further improve the systems for sentiment analysis ofcomments in the Kazakh language, which can be useful in monitoring publicopinion in various areas, including business.