Benchmarking LightGBM and BiLSTM for Sentiment Analysis on Indonesian E-Commerce Reviews

TL;DR

This paper compares LightGBM and BiLSTM for sentiment analysis on Indonesian e-commerce reviews, finding BiLSTM superior in accuracy and context capturing, with LightGBM being highly efficient.

Contribution

It provides a comparative analysis showing BiLSTM's effectiveness over traditional ML models for Indonesian sentiment analysis.

Findings

BiLSTM achieved 98.87% accuracy and F1-Score.

LightGBM achieved 98.23% accuracy with efficient training.

BiLSTM better captures sequential context in Indonesian reviews.

Abstract

This study presents a comparative analysis between two primary approaches in Natural Language Processing (NLP): Machine Learning (ML) utilizing the PyCaret AutoML framework, and Deep Learning (DL). The evaluation is conducted on a sentiment analysis task using an Indonesian e-commerce review dataset sourced from Hugging Face. The dataset, consisting of 15,000 samples, is partitioned into training, validation, and testing sets. The ML experiments compare LightGBM, Logistic Regression, and Support Vector Machine (SVM) algorithms, whereas the DL experiment implements a Bidirectional Long Short-Term Memory (BiLSTM) architecture. The experimental results demonstrate that the BiLSTM model outperforms all ML models, achieving an accuracy of 98.87\% and an F1-Score of 98.87\%. Meanwhile, LightGBM emerges as the best-performing ML model with an accuracy of 98.23\% in a highly efficient training time. This research proves that the BiLSTM architecture is highly capable of capturing the sequential context of Indonesian review texts, making it the superior model for this specific classification task.