EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sentence-Level Sentiment Analysis of Indonesian App Reviews Using IndoBERTweet

Inge Najwa Aqiilah, Ristu Saptono, Akhmad Syaifuddin

Journal of Computing Theories and Applications · 21.06.2026 · 4 (1) · 74-91

DOI: 10.62411/jcta.16240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing Theories and Applications, online erschienen am 21.06.2026. Verfasst von Inge Najwa Aqiilah und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Document-level sentiment analysis assigns a single polarity label to an entire review, often obscuring opinion diversity within multi-sentence submissions. This limitation is particularly evident in reviews of multi-service platforms, where users frequently express heterogeneous opinions toward different aspects of the platform in the same review. To address this challenge, this study proposes a sentence-level sentiment analysis framework for Indonesian Gojek app reviews collected from the Google Play Store. The proposed framework introduces a two-stage segmentation strategy that combines punctuation-aware rules with conjunction-aware splitting based on coordinating and adversative conjunctions (e.g., tapi [but], padahal [even though]) to identify opinion boundaries and decompose mixed-sentiment reviews into independently classifiable sentence units. A total of 14,730 raw reviews collected between May and July 2025 were subjected to data cleaning and quality filtering, resulting in 7,187 valid reviews that were further segmented into 14,187 sentence-level instances. Each instance was manually annotated by three annotators using a four-class labeling scheme consisting of app-positive, app-negative, app-neutral, and service categories. Sentiment-level inter-annotator agreement, computed on the subset of instances unanimously categorized as app-related by all three annotators (n = 4,384), achieved substantial agreement (Fleiss' = 0.636). Hyperparameter optimization was conducted using Optuna with the Tree-structured Parzen Estimator (TPE) sampler across four experimental scenarios. The best performance was achieved by IndoBERTweet under Stratified K-Fold evaluation, attaining an accuracy of 0.751 and a macro F1-score of 0.729, outperforming all IndoBERT configurations. The results demonstrate the effectiveness of domain-adaptive pre-training on informal Indonesian text and highlight the value of conjunction-aware segmentation for preserving fine-grained opinion structures in mixed-sentiment reviews. These findings suggest that domain-aligned language representations provide a practical and effective solution for sentence-level sentiment analysis of Indonesian app reviews.

Zitieren

APA

Aqiilah, I. N., Saptono, R., & Syaifuddin, A. (2026). Sentence-Level Sentiment Analysis of Indonesian App Reviews Using IndoBERTweet. Journal of Computing Theories and Applications, 4(1), 74-91. https://doi.org/10.62411/jcta.16240

Vancouver

Aqiilah IN, Saptono R, Syaifuddin A. Sentence-Level Sentiment Analysis of Indonesian App Reviews Using IndoBERTweet. Journal of Computing Theories and Applications. 2026;4(1):74-91. doi:10.62411/jcta.16240

BibTeX
@article{Aqiilah2026,
  author = {Aqiilah, Inge Najwa and Saptono, Ristu and Syaifuddin, Akhmad},
  title = {Sentence-Level Sentiment Analysis of Indonesian App Reviews Using IndoBERTweet},
  journal = {Journal of Computing Theories and Applications},
  year = {2026},
  volume = {4},
  number = {1},
  pages = {74--91},
  doi = {10.62411/jcta.16240}
}
Kostenlos starten →