Analisis Sentimen Menggunakan Algoritma Naïve Bayes, KNN, dan Decision Tree Terhadap Ulasan Aplikasi KitaLulus

The advent of digital technologies has transformed interaction dynamics between companies and potential employees by creating job search platforms. KitaLulus, one of the leading platforms in Indonesia, facilitates the job search process by providing various vacancies from various companies on one platform. However, there are several complaints from users, such as a complex job application process, inefficient file storage, and poor user interface (UI) and user experience (UX). On the other hand, Twitter is one of the places that contains user reviews, both in the form of satisfaction or disappointment, so that it can be used to identify public sentiment towards the KitaLulus application. Since it is important for the current generation, it is necessary to have a quality job search application, where recommendations for improving the quality of the application can be obtained from sentiment analysis. Therefore, sentiment analysis was conducted to identify public sentiment towards the KitaLulus application. The analysis in this study used 600 review data from Twitter which were then classified by sentiment based on Naïve Bayes, KNN, and Decision Tree algorithms. This research consists of six stages, namely data collection, data cleaning, data labelling, data preprocessing starting from SMOTE, split data, transform cases, tokenize, filter stopwords, and filter tokens (by length), sentiment classification, and finally results and evaluation. The results, after SMOTE was applied at the preprocessing stage, showed that KNN was the best algorithm with accuracy of 83.33%, precision of 80.36%%, and recall of 71.09%, followed by Naïve Bayes and Decision Tree respectively.