Comparative Analysis of AutoML and BiLSTM Models for Cyberbullying Detection on Indonesian Instagram Comments

TL;DR

This study compares traditional machine learning and deep learning models, including BiLSTM with Attention, for detecting cyberbullying in Indonesian Instagram comments, emphasizing domain-specific preprocessing.

Contribution

It provides a comparative analysis of ML and deep learning approaches for Indonesian cyberbullying detection, highlighting preprocessing importance and model performance.

Findings

Logistic Regression outperforms other ML models.

BiLSTM with Attention achieves the best deep learning results.

Preprocessing tailored to Indonesian slang improves detection accuracy.

Abstract

This study compares machine learning and deep learning approaches for cyberbullying detection in Indonesian-language Instagram comments. Using a balanced dataset of 650 comments labeled as Bullying and Non-Bullying, the study evaluates Naive Bayes, Logistic Regression, and Support Vector Machine with TF-IDF features, as well as BiLSTM and BiLSTM with Bahdanau Attention. A preprocessing pipeline tailored to informal Indonesian text is applied, including slang normalization, stopword removal, and stemming. The results show that Logistic Regression performs best among the machine learning models, while BiLSTM with Attention achieves the strongest overall deep learning performance. The findings highlight the value of domain-specific preprocessing and show that although deep learning captures contextual patterns more effectively, machine learning remains a competitive option for resource-constrained deployments.