Thai Sentiment Analysis for Social Media Monitoring using Machine Learning Approach

Sentiment analysis has become essential in marketing research to understand customer attitudes or opinions. This research proposes a Thai sentiment analysis framework for social media. Our framework is a four-step process that is very simple and easy to implement. To create an effective framework, the proposed method was tested on two different datasets for further support in any domain. The experiments were conducted on ten well-known classifiers from the Scikit-learn library. The comparative performance of machine learning algorithms for sentiment analysis shows that Logistic Regression and SVM yield the highest accuracy.