Machine Learning
LSTM-Based Customer Feedback Classification in Indonesian
This study implements LSTM neural networks with FastText word embeddings for multi-class classification of Indonesian customer reviews into categories: Account, Application, Customer Service, and Transaction.
LSTM Deep Learning NLP Text Classification PyTorch Indonesian Language
Project Overview
Customer feedback is crucial for understanding user needs and improving service quality. This project implements a deep learning pipeline to automatically classify Indonesian customer reviews into four categories:
- Akun (Account) - Issues related to user accounts
- Aplikasi (Application) - Problems with the app itself
- Layanan Pelanggan (Customer Service) - Customer support related
- Transaksi (Transaction) - Issues with payments and transactions
Key Features
- 🧹 Text Preprocessing - Cleaning, normalization, and tokenization for Indonesian text
- 📊 FastText Embeddings - Pre-trained Indonesian word vectors (300 dimensions)
- 🧠 LSTM Architecture - Bidirectional processing with avg/max pooling
- 📈 5-Fold Cross Validation - Robust model evaluation
- 🎯 ~85% Accuracy - Strong performance on the test set
Interactive Notebook
The complete experiment notebook with code, outputs, and visualizations:
Loading notebook...