Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 15, 2025JIKO (Jurnal Informatika dan Komputer)

Evaluation of Indobert and Roberta: Performance of Indonesian Language Transformer Models in Sentiment Classification

View Full Paper
Ask AI
Bookmark
Share

Authors

MNM. Adnan NurMuhammadiyah University of MakassarNUNajirah UmarMuhammadiyah University of MakassarZFZhipeng Feng

Discussion

Loading...

Member takes

Implication

This analysis compares IndoBERT and RoBERTa models in sentiment classification, revealing IndoBERT's superior performance.

Key Points

  • IndoBERT achieved an accuracy of 70%, outperforming RoBERTa's 67%, indicating its effectiveness in sentiment classification.
  • The average F1-score of IndoBERT is 0.69, compared to RoBERTa's 0.65, suggesting better balance in classifying sentiment categories.
  • IndoBERT demonstrated lower evaluation loss values, indicating superior generalization capability in understanding the Indonesian context.
  • Faster and more stable training times were observed for IndoBERT, emphasizing its efficiency over RoBERTa.

Cite This Study

Nur et al. (2025) studied this question.

synapsesocial.com/papers/68af4ec6ad7bf08b1ead8153https://doi.org/10.33387/jiko.v8i2.9988
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Sentiment Classification of Indonesian-Language Roblox Reviews Using IndoBERT with SMOTE Optimization2025 · 2 citations
  2. 2Sentiment analysis of student evaluation feedback using transformer-based language models2024 · 9 citations
  3. 3Optimizing BERT Models with Fine-Tuning for Indonesian Twitter Sentiment Analysis2025 · 4 citations
  4. 4ABSA of Indonesian customer reviews using IndoBERT: single- sentence and sentence-pair classification approaches2024 · 27 citations
  5. 5Implementation of IndoBERT for Sentiment Analysis of the Constitutional Court's Decision Regarding the Minimum Age of Vice Presidential Candidates2025 · 4 citations