Sentiment Classification of Social Media Data for Telecommunication Companies in Turkey

Abstract

In recent years, the huge amount of data that has emerged in the world as a result of a very rapid increase in digital data has brought about the storage, processing and analysis of data into business intelligence solutions. One of the biggest sources of this large-scale data that has emerged and continues to grow is the data produced from social media tools. The average daily amount generated by Twitter social media is around 7 terabytes and this value increases day by day. Twitter is a social media tool that users express their feelings and thoughts about commercial companies, about social events, or sharing in any subject. In this study, a sentiment classification study was carried out on the tweets that were taken in the two selected date ranges of two major telecommunication companies serving in Turkey. The feature vectors obtained by two different feature extraction methods from the tweets where the users shared are classified as 'positive/negative' by using KNN classifier. In this way, Twitter users' thoughts and satisfaction about three telecommunication companies in Turkey were determined in two selected dates. © 2017 IEEE.