@article {10.3844/jcssp.2025.158.167,
article_type = {journal},
title = {Sentiment Analysis on User Reviews of Snapchat in Indonesia},
author = {Madyatmadja, Evaristus Didik and Winata, Brigita Christabel Surya and Pradhan, Evelyn and Yasmina, Fathya Putri and Adrian, Feladiva Annrastia and Mahardhika, Raihan and Christian, and Sembiring, David Jumpa Malem},
volume = {21},
number = {1},
year = {2025},
month = {Jan},
pages = {158-167},
doi = {10.3844/jcssp.2025.158.167},
url = {https://thescipub.com/abstract/jcssp.2025.158.167},
abstract = {This research explores the sentiment expressed in Snapchat user reviews within the Indonesian context, leveraging advanced natural language processing techniques and classification models. With a focus on the Indonesian user base, 8,015 reviews from the Google Play Store were analyzed using naive bayes, Support Vector Machines (SVM), and random forest models. The results indicated that the random forest model outperformed others with an 83% accuracy rate, followed by SVM at 81% and naive bayes at 80%. The analysis of frequently mentioned words in positive and negative reviews unveiled key aspects influencing user satisfaction. Positive reviews highlighted terms like 'bagus' (good) and 'suka' (like), while negative reviews often mentioned 'jelek' (bad) and technical issues like 'download.' The study contributes valuable insights for developers to enhance user experience on the Snapchat platform and suggests directions for future research in sentiment analysis of social media reviews.},
journal = {Journal of Computer Science},
publisher = {Science Publications}
}