Sentiment Analysis of Online Transportation Service using the Naïve Bayes Methods

• Published in: Journal of physics. Conference series Vol. 1641; no. 1; pp. 12093 - 12098
• Main Authors: Tika Adilah, M, Supendar, Hendra, Ningsih, Rahayu, Muryani, Sri, Solecha, Kusmayanti
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.11.2020
• Subjects: Data mining; Digital media; Physics; Sentiment analysis; Social networks; Transportation services
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/1641/1/012093

Sentiment analysis is a computational study of opinions and emotions expressed textually. Sentiment analysis will group text in sentences or documents to find out the opinions expressed in the sentence or document, whether negative or positive. This sentiment analysis research was conducted on the online taxi transportation service. Gojek uses a lot of social media to communicate with its customers, one of the social media used is Instagram. This research takes 1000 comments from the Instagram of the Gojek page which is used to see the public opinion of the online Gojek transportation services. Comments from the page are processed by doing text preprocessing and then classified using the Naive Bayes Classifier (NBC) method to obtain the value of the public value for online transportation services. The results of this study using the Naive Bayes method resulted in an accuracy value of 81.00%, which means that from all the comments on the Instagram page, the subject of the NBC method could be accurately classified by 81.00% whether the comments were negative or positive comments.