Abstract
The mobile application (or usually known as mobile app) market has grown drastically over the last 15 years. Based on this fact, it is important for app developer to keep their engagement with their user by understanding their user's needs. Lexicon based sentiment analysis is a method that can be used for determining the sentiment polarization of a review or a comment in the App Store. There are two resources needed in lexicon based sentiment analysis for Indonesian language: machine translation and lexicon resource. In this study, we compare the performance of several different combinations of machine translations and lexicon resources in order to know the best resource combination that can be used in lexicon based sentiment analysis on App Review. The result shows that the combination of Google Translate and SentiWordNet can reach the highest overall accuracy by getting the score 0.72.

This publication has 16 references indexed in Scilit: