Analisis Sentimen Ulasan Pengguna Aplikasi Jalan Kita 2.0 Menggunakan Metode Algoritma Naïve Bayes
Abstrak
User reviews of the Jalan Kita 2.0 application represent a valuable source of information for evaluating the quality of application-based road infrastructure reporting services. However, these reviews are expressed as unstructured text, which makes manual analysis inefficient and prone to subjectivity. This study aims to analyze the sentiment of user reviews of the Jalan Kita 2.0 application using the Multinomial Naïve Bayes algorithm. The dataset was collected from the Google Play Store and processed through several text preprocessing stages, including case folding, tokenization, stopword removal, and stemming. Feature extraction was performed using the Term Frequency–Inverse Document Frequency (TF-IDF) method. A total of 334 reviews were analyzed and classified into two sentiment categories, namely positive and negative, with the data split into training and testing sets using an 80:20 ratio. The results show that positive sentiment dominates the user reviews, accounting for 81.44% of the dataset, indicating that most users perceive the application as beneficial for reporting road infrastructure issues. Model evaluation achieved an accuracy of 0.93, with precision, recall, and F1-score values of 0.93, 0.93, and 0.92, respectively. These findings demonstrate that the Multinomial Naïve Bayes algorithm performs effectively in classifying sentiment in user reviews of the Jalan Kita 2.0 application and can be utilized as a data-driven basis for evaluating and improving the quality of public service applications.
Identifier
- DOI: https://doi.org/10.24252/shift.v6i1.271
- OpenAlex: https://openalex.org/W7167335389