Oct 2026· JOURNAL OF APPLIED INFORMATICS AND COMPUTING· 0 citations· 21 references
TL;DR
The findings show that preprocessing effectiveness depends on model architecture, and minimal preprocessing better preserves contextual information for IndoRoBERTa, whereas aggressive preprocessing provides only a marginal benefit for the static baseline.
Abstract
This study evaluates the effects of heavy and minimal preprocessing on static and contextual text representations for sentiment classification of Indonesian Shopee reviews. The dataset comprised 29,618 Google Play Store reviews collected in January 2026 and weakly labeled from star ratings into negative, neutral, and positive classes. The data were divided into training, validation, and test sets using an 80:10:10 stratified split. Heavy preprocessing included case folding, text cleaning, slang normalization, stopword removal, and stemming, whereas minimal preprocessing applied case folding only. Four experimental configurations combined the two preprocessing strategies with Word2Vec–Logistic Regression and fine-tuned IndoRoBERTa. Model performance was evaluated using accuracy, weighted precision, weighted recall, weighted F1-score, macro F1-score, and confusion matrices. Heavy preprocessing produced a marginal weighted F1-score improvement for Word2Vec–Logistic Regression, from 86.0% to 86.2%. Minimal preprocessing improved IndoRoBERTa’s weighted F1-score from 88.4% to 89.7% and achieved the best accuracy of 90.7% and macro F1-score of 65.8%. The difference between weighted and macro F1-scores indicates that the neutral minority class remained difficult to identify. The findings show that preprocessing effectiveness depends on model architecture. Minimal preprocessing better preserves contextual information for IndoRoBERTa, whereas aggressive preprocessing provides only a marginal benefit for the static baseline.
Purpose: Selecting optimal text-processing methods for sentiment analysis of digital financial application reviews, especially in Indonesian, is challenging. Previous studies have typically evaluated preprocessing techniques, feature engineering methods, and classification models in isolation, leaving the question of t...
Samsudin Samsudin, Linda Putriani· Scientific Journal of Inform...· 0 citations
The growth of user generated content on social media has increased the need for automatic sentiment analysis of unstructured text. This research fine tuned an IndoBERT based architecture for ternary sentiment classification of 3,857 TikTok comments on Point Coffee, collected between January 2020 and February 2025. The...
Romindo, K. Sirait, Triandes Sinaga et al.· 2026 3rd International Confe...· 0 citations
Consumer reviews on Indonesian e-commerce platforms now arrive faster than manual analysis can process them, and IndoBERT has become a common choice for classifying them automatically. Many studies, however, train on a single data source and report one training run, with no documented hyperparameter search and no test...
Aditya Rahmatullah, A. Rizaldy, Syahbudin et al.· Journal of Artificial Intell...· 0 citations
User reviews on Google Play Store contain opinions that can be used to evaluate digital applications, but large review volumes make manual analysis inefficient. This study analyzes 8,000 ChatGPT reviews collected from January to May 2026 using the CRISP-DM framework. Text preparation includes case folding, cleaning, to...
G. Handayani, Hotler Manurung, Melda Pita Uli Sitompul· Journal of Artificial Intell...· 0 citations
Multi-domain sentiment classification remains challenging because lexical polarity and expression patterns vary across application contexts. This study evaluates an enhanced iVADER framework that combines domain-specific lexicon adaptation with text preprocessing and machine-learning-supported feature representations....
Saleh Yaakub, M. Deris, I. Windiarti· Jurnal RESTI (Rekayasa Siste...· 0 citations
This study investigates sentiment classification on imbalanced Indonesian user-review data from the MyIM3 mobile application, focusing on the effectiveness of hierarchical data augmentation for improving minority-class detection. A total of 10,000 reviews were collected, of which 6,968 were retained after preprocessing...
Sang Ayu Putu Diah Setyawati, Roy Rudolf Huizen, Dadang Hermawan· Jurnal Teknik Informatika (J...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.