EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Modeling Sentiment Patterns in Indonesian Gojek Reviews with TF-IDF and Support Vector Machine

Angel Gloria Simanullang, Yashelter Aenjealik Nazara, Seikel Krina Michi Berutu, Marisa Aurelia Damanik, Aryapto Pardosi Pardosi

JADEN : Journal of Algorithmic Digital Engineering and Networks · 29.01.2026 · 1 (2) · 49-63

DOI: 10.65853/jaden.v1i2.121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JADEN : Journal of Algorithmic Digital Engineering and Networks, online erschienen am 29.01.2026. Verfasst von Angel Gloria Simanullang und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of mobile-based ride-hailing services in Indonesia has significantly increased the use of digital platforms such as Gojek. This growth has generated a large volume of user reviews on the Google Play Store, reflecting user experiences, perceptions, and satisfaction levels. However, manual analysis of these reviews is inefficient due to their volume and subjective nature. Therefore, this study aims to model sentiment patterns in Indonesian Gojek user reviews using a machine learning approach. This research applies the Support Vector Machine (SVM) algorithm combined with Term Frequency–Inverse Document Frequency (TF-IDF) for feature extraction. The dataset consists of 5,000 Indonesian-language user reviews collected from the Google Play Store. Text preprocessing includes case folding, cleaning, tokenizing, stopword removal, and stemming. Sentiment labeling is performed automatically using a lexicon-based approach, classifying the data into positive, negative, and neutral categories. The results indicate that neutral sentiment dominates the dataset (60.26%), followed by positive (31.34%) and negative (8.40%) sentiments. The SVM model achieves an accuracy of 72.58%. The neutral class shows the highest recall (99.17%), while the positive class achieves the highest precision (99.65%). These findings indicate that TF-IDF and SVM are effective for modeling sentiment patterns, although challenges remain in handling ambiguous expressions, such as sarcasm or mixed sentiments, which can lead to misclassification.

Zitieren

APA

Simanullang, A. G., Nazara, Y. A., Berutu, S. K. M., Damanik, M. A., & Pardosi, A. P. (2026). Modeling Sentiment Patterns in Indonesian Gojek Reviews with TF-IDF and Support Vector Machine. JADEN : Journal of Algorithmic Digital Engineering and Networks, 1(2), 49-63. https://doi.org/10.65853/jaden.v1i2.121

Vancouver

Simanullang AG, Nazara YA, Berutu SKM, Damanik MA, Pardosi AP. Modeling Sentiment Patterns in Indonesian Gojek Reviews with TF-IDF and Support Vector Machine. JADEN : Journal of Algorithmic Digital Engineering and Networks. 2026;1(2):49-63. doi:10.65853/jaden.v1i2.121

BibTeX
@article{Simanullang2026,
  author = {Simanullang, Angel Gloria and Nazara, Yashelter Aenjealik and Berutu, Seikel Krina Michi and Damanik, Marisa Aurelia and Pardosi, Aryapto Pardosi},
  title = {Modeling Sentiment Patterns in Indonesian Gojek Reviews with TF-IDF and Support Vector Machine},
  journal = {JADEN : Journal of Algorithmic Digital Engineering and Networks},
  year = {2026},
  volume = {1},
  number = {2},
  pages = {49--63},
  doi = {10.65853/jaden.v1i2.121}
}
Kostenlos starten →