Sentiment Analysis of Indonesian-Language Plantix Application Reviews for Plant Disease Diagnosis Using Naive Bayes Methods

Abstract

The Plantix app is one of the digital solutions widely utilized by farmers to diagnose plant diseases through image recognition technology and support from the user community. The large amount of Indonesian-language customer feedback on Google's application can be a valuable source of information for assessing the effectiveness and user satisfaction of this application. This study uses naive Bayes algorithms to classify sentiments based on the Plantix application's customer feedback. The dataset was obtained by implementing web scraping techniques with the Google Play scraper library, resulting in more than 354 reviews. Data preprocessing stages include case folding, text cleaning, tokenization, stemming using the Sastrawi library, and text transformation into numerical form using the Term Frequency-Inverse Document Frequency (TF-IDF) method. Sentiment labels are determined based on user star ratings, which are divided into three categories: positive, neutral, and negative. The Multinomial Naive Bayes algorithm performs the classification process and is assessed through the K-fold Cross Validation technique (K=10). The assessment results show that the model achieves the highest accuracy of 75.10% and F1-score of 72.35% with the shuffle sampling method, which falls into the category of fairly good classification. This study demonstrates that naive Bayes methodology is effectively used in sentiment analysis of text-based agricultural application reviews in Bahasa Indonesia.