Analisis Sentimen Penggunaan Aplikasi Traveloka di Twitter Menggunakan Model Klasifikasi

Abstract

Traveloka is an online travel platform that provides booking services for transportation tickets, accommodation, tourist attraction entrance tickets, and others. This research will conduct sentiment analysis using five methods and conduct a comparative analysis between these methods. The goal is to find out how to do sentiment analysis and do a comparison analysis and get the best results for Traveloka sentiment analysis on Twitter. This research uses Twitter to get data and only focuses on tweets about Traveloka. Sentiment analysis also provides benefits for Traveloka in monitoring and analyzing user responses to their products and services from reviews and feedback posted by users on social media such as Twitter, Traveloka can gain valuable insights into the strengths and weaknesses of their services. This dataset consists of 85.6% positive sentiments and 14.4% negative sentiments. In this analysis, the library used is Scikitlearn. Five classification methods were used, namely, Random Forest (RF), Support Vector Machine (SVM), Naive Bayes Classifier (NBC), K-Nearest Neighbor (KNN), and XGBOOST. The steps in this research are data crawling, data preprocessing, data weighting, classification, model testing, model evaluation, comparison analysis, and result analysis. The results show that SVM has better accuracy based on metric evaluation with a value of 90%. However, through model testing using AUC, XGBOOST obtained the highest value of 71%.