An Evaluation of User Satisfaction with the Ruangguru EdTech App Using a Lexicon-Based Sentiment Analysis Approach
Abstrak
The development of educational technology (EdTech) in Indonesia has established Ruangguru as one of the largest online learning platforms. Users of Ruangguru’s EdTech platform can provide feedback regarding their satisfaction and complaints directly via the Google Play Store. Manually evaluating thousands of reviews would be inefficient; therefore, an automated approach is required to understand user perceptions. This study aims to evaluate the level of user satisfaction with the Ruangguru app by classifying user reviews into positive, negative or neutral sentiment groups. The results of this classification can be used to identify aspects of the service that need to be improved in the Ruangguru app. This study employs a Lexicon-Based Sentiment Analysis approach. Data was collected via user review scraping on the Google Play Store. The research stages included data preprocessing (case folding, data cleaning, normalisation, stopword removal and stemming), sentiment scoring and labelling using an Indonesian lexicon, and sentiment distribution analysis. The results of the study, conducted on 1,000 user reviews, showed that approximately 75.2% fell into the positive sentiment category, 22.1% into the neutral sentiment category, and 2.7% into the negative sentiment category. Users were predominantly positive, expressing satisfaction with the Ruangguru learning app. This study demonstrates that the Lexicon approach is effective in classifying the sentiment of user reviews. The evaluation results can serve as a reference for Ruangguru’s developers to improve features and enhance service quality in the future. Further research could be conducted using a larger dataset, a longer data collection period, reviews in various languages, and the exploration of other sentiment analysis approaches such as Machine Learning (Naive Bayes, SVM, Random Forest) or Deep Learning (CNN, BERT, RNN).
Identifier
- DOI: https://doi.org/10.63956/jitar.v2i1.64
- OpenAlex: https://openalex.org/W7171641948