Projects AI/ML
06
Simobi+ Review Sentiment Analysis
Processed app reviews and compared SVM, Bi-LSTM, and IndoBERT for sentiment classification. Used manual annotation and pseudo-labeling to explore learning from limited labeled data, with separate preprocessing and evaluation notebooks.
Project Preview 01 / 01
Ownership
Personal Project
Role
Machine Learning Engineer
Team
Independent Project
My Role
- 01 Prepared and cleaned mobile-app review data.
- 02 Compared classical, recurrent, and transformer-based classifiers.
- 03 Evaluated the effect of manual annotation and pseudo-labeling.
Features
- 01 Review preprocessing
- 02 Manual annotation workflow
- 03 SVM baseline
- 04 Bi-LSTM classifier
- 05 IndoBERT comparison
Impact
- Provided a comparative view of sentiment modeling approaches for Indonesian app reviews.
Tech Stack
PythonIndoBERTBi-LSTMLabel StudioPseudo-labeling