Sentiment Analysis on User Reviews of Strava Mobile Application in Indonesia

A popular smartphone software for sports and fitness lovers, Strava lets users track, evaluate, and share their physical activity. More than 120 million people use Strava globally as of 2023, and about 2 million new users sign up each month. Performance monitoring, route heat maps, and social network integration are just a few of the app's great features. Given its increasing popularity. Using three machine learning models Naïve Bayes, Support Vector Machine (SVM), and Random Forest this study seeks to examine user sentiment regarding Strava. In order to achieve the best possible balance between learning and model evaluation, the data in this study is split <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$80: 20$</tex>, with 80 % going into model training and the remaining 20% into testing. The purpose of this study is to determine which algorithm is best for categorizing the sentiment of Strava user reviews by comparing the three models. This study analyzes user sentiment toward Strava using three machine learning models: Random Forest, Support Vector Machine (SVM), and Naïve Bayes. The data in this study was split <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$80: 20$</tex>, with 80 percent going toward training and the remaining 20 percent going toward testing, in order to guarantee the best possible balance between the models' learning and evaluation processes. This study compares the three models in order to determine which algorithm is best for categorizing the sentiment of user reviews on Strava.