EUVIMEDEUVIMED entdecken
Crossref

Topic Analysis Using LDA-LSTM on Shopee User Comment

Shannon Dominique Saputra, Albertus Dwiyoga Widiantoro Dwiyoga Widiantoro

SISFORMA · 30.06.2026 · 13 (1) · 36-42

DOI: 10.24167/sisforma.v13i1.15534 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SISFORMA, online erschienen am 30.06.2026. Verfasst von Shannon Dominique Saputra und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Shopee's growth has also shaped online shopping in Indonesia. This study analyzed user reviews to measure satisfaction and identify key service issues using a hybrid framework: LDA for topic modeling and LSTM for sentiment classification. Class imbalance was addressed using a combination of Random Oversampling and Neighborhood Cleaning Rule (ROS-NCL).The results showed that LSTM + ROS-NCL outperformed ROS, NCL, and SMOTE, with 95% accuracy and a precision, recall, and F1-score of 0.94 each. These findings demonstrate that oversampling combined with noise cleaning effectively improves performance on imbalanced data, while also providing practical insights for feature development, logistics improvements, and Shopee's promotional strategy.

Zitieren

APA

Saputra, S. D., & Widiantoro, A. D. W. D. (2026). Topic Analysis Using LDA-LSTM on Shopee User Comment. SISFORMA, 13(1), 36-42. https://doi.org/10.24167/sisforma.v13i1.15534

Vancouver

Saputra SD, Widiantoro ADWD. Topic Analysis Using LDA-LSTM on Shopee User Comment. SISFORMA. 2026;13(1):36-42. doi:10.24167/sisforma.v13i1.15534

BibTeX
@article{Saputra2026,
  author = {Saputra, Shannon Dominique and Widiantoro, Albertus Dwiyoga Widiantoro Dwiyoga},
  title = {Topic Analysis Using LDA-LSTM on Shopee User Comment},
  journal = {SISFORMA},
  year = {2026},
  volume = {13},
  number = {1},
  pages = {36--42},
  doi = {10.24167/sisforma.v13i1.15534}
}
Kostenlos starten →