A multi-task BiLSTM with shared encoder and AutoML pipeline classifies sentiment and emotions on the PRDECT-ID Indonesian review dataset with public code and Gradio demos.
Comparative study of BiLSTM and GRU for sentiment analysis on indonesian e-commerce product reviews using deep sequential modeling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
BiLSTM achieves 98.87% accuracy and F1-score on Indonesian e-commerce review sentiment analysis, slightly outperforming the best machine learning model LightGBM at 98.23%.
citing papers explorer
-
Sentiment and Emotion Classification of Indonesian E-Commerce Reviews via Multi-Task BiLSTM and AutoML Benchmarking
A multi-task BiLSTM with shared encoder and AutoML pipeline classifies sentiment and emotions on the PRDECT-ID Indonesian review dataset with public code and Gradio demos.
-
Benchmarking LightGBM and BiLSTM for Sentiment Analysis on Indonesian E-Commerce Reviews
BiLSTM achieves 98.87% accuracy and F1-score on Indonesian e-commerce review sentiment analysis, slightly outperforming the best machine learning model LightGBM at 98.23%.