Twitter sentiment analysis of online transportation service providers

Abstract

GO-JEK and Grab are two most popular online transportation service providers in Indonesia. The competition between the two is tight to acquire new customers and provide the best service. No official survey has been conducted in measuring customer satisfaction at both companies to give insight which company offers better service quality. This study aims to measure GO-JEK and Grab customer satisfaction through sentiment analysis of Twitter's data. Both companies use Twitter to reach their customers and promote their service. We collect 126,405 tweets from February to March 2016 containing GO-JEK and Grab keywords. Then, we pre-process the tweets and label manually before they are classified using three algorithms: Support Vector Machine, Naïve Bayes, and Decision Tree. We made and compared several classification schemes with different keywords, dataset, and k-fold cross validation techniques. Finally, we calculate Net Sentiment Score which correlates with customer satisfaction using classification results. The experiments shows that Grab's customer satisfaction is higher than GO-JEK's. The study also shows that customers tend to mention both companies Twitter account for bad experiences and not mentioning company's account for positive comments.