A Trustable LSTM-Autoencoder Network for Cyberbullying Detection on Social Media Using Synthetic Data

TL;DR

This paper introduces a trustable LSTM-Autoencoder network that effectively detects cyberbullying on social media across multiple languages, utilizing synthetic data to overcome data scarcity and outperforming existing models with 95% accuracy.

Contribution

The paper presents a novel LSTM-Autoencoder model trained on synthetic data, addressing language data scarcity and achieving state-of-the-art cyberbullying detection performance.

Findings

The proposed model achieved up to 95% accuracy.

It outperformed traditional models like LSTM, BiLSTM, and BERT.

Synthetic data helped improve detection across Hindi, Bangla, and English.

Abstract

Social media cyberbullying has a detrimental effect on human life. As online social networking grows daily, the amount of hate speech also increases. Such terrible content can cause depression and actions related to suicide. This paper proposes a trustable LSTM-Autoencoder Network for cyberbullying detection on social media using synthetic data. We have demonstrated a cutting-edge method to address data availability difficulties by producing machine-translated data. However, several languages such as Hindi and Bangla still lack adequate investigations due to a lack of datasets. We carried out experimental identification of aggressive comments on Hindi, Bangla, and English datasets using the proposed model and traditional models, including Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), LSTM-Autoencoder, Word2vec, Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-trained Transformer 2 (GPT-2) models. We employed evaluation metrics such as f1-score, accuracy, precision, and recall to assess the models performance. Our proposed model outperformed all the models on all datasets, achieving the highest accuracy of 95%. Our model achieves state-of-the-art results among all the previous works on the dataset we used in this paper.