Social media sentiment analysis with data mining techniques

Due to the increase in internet access opportunities and the widespread use of smartphones in recent years, the services called social media, where people share their opinions on various issues, have started to be used widely. The data entered by users into these services and stored on many different platforms are analyzed by various data mining methods and meaningful information inferences are tried to be made. Sentiment Analysis studies, which means making meaningful inferences about people's feelings on different subjects by analyzing social media data, is one of the prominent fields of study in this regard. Sentiment Analysis is the process of categorizing people's opinions according to various classes such as positive, negative or neutral. And in terms of businesses, it is actively used in many sectors such as understanding the behavioral tendencies of its customers, evaluating the mental health of patients, revealing the reactions of people in various social events. In this thesis, a labeled data set consisting of movie reviews shared by users on the IMDB website was classified using various data mining methods, a sentiment analysis study was carried out with Python, Matlab and R programming languages, and the results were compared according to different evaluation criteria.