APLIKASI MOBILE UNTUK ANALISIS SENTIMEN PADA GOOGLE PLAY

• Main Authors: , Lutfi Budi Ilmawan, , Drs. Edi Winarko, M.Sc.,Ph.D
• Format: Theses and Dissertations NonPeerReviewed
• Published: [Yogyakarta] : Universitas Gadjah Mada 2014
• Subjects: ETD
• Online Access: https://repository.ugm.ac.id/130539/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=70963
• Institution: Universitas Gadjah Mada

Google�s application store, Google Play is now providing approximately 1,200,000 mobile applications. With a number of these applications make android users have difficulties in determining their choice. This was handled by Google Play by providing textual review of the application, but it is also a challenge for users to read a lot of comments. In addition, application developers have difficulty in figuring out how to improve their application performance by thousands of comment. With these problems, it needs a sentiment analysis applications that can process a number of comments to get information, this information would have the added value as knowledge of something. The basic task of sentiment analysis is classifying polarity of text that contains the opinions and emotions. The purpose of this system is determining the polarity of sentiments from application�s textual reviews on Google Play that can be performed on mobile devices. The mobile device has high portability and the majority of these devices have limited resource. That problem can be solved by using a client server based system architecture, where the server performs training and classification tasks while clients is a mobile device that perform some of sentiment analysis task that can be running on small resource mobile device. With this solution the sentiment analysis could be applied to the mobile environment. The classification method that used are Naive Bayes for developed application and Linear Support Vector Machine that is used for comparing. Naïve Bayes classifier�s accuracy is 83.87%. The result is lower than the accuracy value of Linear SVM classifier that reach 89.49%. The use of semantic handling can reduce the accuracy of the classifier.