Sentiment Analysis on Starbucks Reviews: Implementation of K-Nearest Neighbors and Support Vector Machine
Infact: International Journal of Computers · 2025
DOI: 10.61179/infact.v9i02.761 ↗Kurz gefasst
Fachartikel in der Zeitschrift Infact: International Journal of Computers, 2025. Verfasst von Jasmine Nabila und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study conducts sentiment analysis on Starbucks customer reviews from the ConsumerAffairs website using the K-Nearest Neighbors (KNN) classification algorithm. The objective is to evaluate customer satisfaction and perceptions of service. Reviews are preprocessed with standard NLP techniques and labeled using TextBlob based on sentiment polarity: positive, neutral, or negative. The KNN algorithm is tested with different training and testing ratios: 60%:40%, 70%:30%, and 80%:20%. The best accuracy, 85%, is achieved with a 60%:40% split, indicating that a balanced dataset improves performance and reduces overfitting. Results show that most reviews reflect positive sentiment, with words like ‘awesome’, ‘sweet’, and ‘variety’. Nonetheless, some reviews mention negative experiences, especially health-related issues and in-store equipment problems. The KNN method proves effective for sentiment classification and provides meaningful insights that Starbucks can utilize to enhance product quality, service efficiency, and overall customer satisfaction.
Zitieren
APA
Nabila, J., Putra, I. A. D. B., & Wijayanto, H. (2025). Sentiment Analysis on Starbucks Reviews: Implementation of K-Nearest Neighbors and Support Vector Machine. Infact: International Journal of Computers. https://doi.org/10.61179/infact.v9i02.761
Vancouver
Nabila J, Putra IADB, Wijayanto H. Sentiment Analysis on Starbucks Reviews: Implementation of K-Nearest Neighbors and Support Vector Machine. Infact: International Journal of Computers. 2025. doi:10.61179/infact.v9i02.761
BibTeX
@article{Nabila2025,
author = {Nabila, Jasmine and Putra, Ida Ayu Devian Branitasandhini and Wijayanto, Heri},
title = {Sentiment Analysis on Starbucks Reviews: Implementation of K-Nearest Neighbors and Support Vector Machine},
journal = {Infact: International Journal of Computers},
year = {2025},
doi = {10.61179/infact.v9i02.761}
}
EUVIMED