Sentiment analysis methods on big data and application to Azerbaijan language

In recent days microblog sites have become a very popular means of communication among internet users. Millions of users share their opinions and feelings about different aspects of their lives in different blocks every day. For this reason, microblog sites are translated into rich data sources for idea mining and sentiment analysis. Sentiment Analysis (SA) is an ongoing research area in the field of text mining. The task of Sentiment Analysis is to label people's views from a given text into different categories, such as positive, negative or neutral. In addition, machine learning methods such as maximum entropy, naive bayes, support vector machine and lexicon based word counting and feature scoring methods were used. The results obtained were compared and the optimal parameters for the classification of tweets were defined. The data used in most of the studies are in English. Therefore, in order to provide more resources in the field of emotion analysis for the Azerbaijani language, it was decided to do a doctoral thesis on this subject. In this study, a hybrid approach was developed to analyze sentiment in the Azerbaijani language. Although the language used in the study is with the Azerbaijani language, the proposed technique can be used with other languages. Keywords: Sentiment Analysis, Classification, Machine Learning, Twitter, Azerbaijani language.