Emoji ikonlarının özellikleri kullanılarak genel Türkçe derlem üzerinde duygu analizinin ölçülmesi

Automatic recognition of feelings in a text is a promising research area which has recently gained more importance with the rapid growth of social media websites, mostly microblogs. The increasing number of user generated text expands the definition of sentiment analysis where the extraction of emotions from user posts becomes a cutting edge. For that reason, the opinion mining becomes a crucial step for the analysis of social behavior in individuals or groups for the detection of trends. In current applications, the language of emojis is considered as a common way or an interlingua to express the ideas or intensify feelings. However, there are few studies to reveal its effects on Turkish context for overlapped and separate senses. In this study, emojis have been used as an identifier of the emotions in Turkish texts. The emotion analysis has been performed by Support Vector Machines (SVM), multinomial Naïve Bayes (NB), FastText and Convolutional Neural Network (CNN) using test and train sets derived from Twitter corpus. The preparation and preprocessing of the corpus have been accomplished by generating the classifiers; groups and emotions. The manually labeled tweets have also been added to evaluate the generic function of the classifier. The use of corpus in a generic domain present a promising field where different emotion states have been measured.