Sentiment and Emotion Classification of Indonesian E-Commerce Reviews via Multi-Task BiLSTM and AutoML Benchmarking

TL;DR

This paper develops and benchmarks a multi-task sentiment and emotion classifier for Indonesian e-commerce reviews, combining AutoML and BiLSTM approaches, with preprocessing tailored for slang and regional language.

Contribution

It introduces a dual-track classification pipeline using AutoML and BiLSTM, tailored preprocessing, and benchmarks multiple configurations on a new Indonesian review dataset.

Findings

AutoML approach achieves competitive baseline results.

BiLSTM models outperform traditional classifiers in this context.

Preprocessing with slang dictionary improves classification accuracy.

Abstract

Indonesian marketplace reviews mix standard vocabulary with slang, regional loanwords, numeric shorthands, and emoji, making lexicon-based sentiment tools unreliable in practice. This paper describes a two-track classification pipeline applied to the PRDECT-ID dataset, which contains 5,400 product reviews from 29 Indonesian e-commerce categories, each labeled for binary sentiment (Positive/Negative) and five-class emotion (Happy, Sad, Fear, Love, Anger). The first track applies TF-IDF vectorization with a PyCaret AutoML sweep across standard classifiers. The second track is a PyTorch Bidirectional Long Short-Term Memory (BiLSTM) network with a shared encoder and two task-specific output heads. A preprocessing module applies 14 sequential cleaning steps, including a 140-entry slang dictionary assembled from marketplace corpora. Four configurations are benchmarked: BiLSTM Baseline, BiLSTM Improved, BiLSTM Large, and TextCNN. Training uses class-weighted cross-entropy loss, ReduceLROnPlateau scheduling, and early stopping. Both tracks are deployed as Gradio applications on Hugging Face Spaces. Source code is publicly available at https://github.com/ikii-sd/pba2026-crazyrichteam.