Abusive comment identification on Indonesian social media data using hybrid deep learning

Abstract

<span lang="EN-US">Half of the entire social media users in Indonesia has experienced cyberbullying. Cyberbullying is one of the treatments received as an attack with abusive words. An abusive word is a word or phrase that contained harassment and is expressed be it spoken or in the form of text. This is a serious problem that must be controlled because the act has an impact on the victim's psychology and causes trauma resulting in depression. This study proposed to identify abusive comments from social media in Indonesian language using a deep learning approach. The architecture used is a hybrid model, a combination between <a name="_Hlk99537661"></a>recurrent neural network (RNN) and long short-term memory (LSTM). RNN can map the input sequences to fixed-size vectors on hidden vector components and LSTM implemented to overcome gradient vector growth components that have the potential to exist in RNN. The steps carried out include preprocessing, modelling, implementation, and evaluation. The dataset used is indonesian abusive and hate speech from Twitter data. The evaluation result showed that the model proposed produced an f-measure value of 94% with an increase in accuracy of 23%.</span>

Hybrid Convolutional Recurrent Neural Network for Cyberbullying Detection on Textual Data

“…The integration of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) architectures has emerged as a promising approach for cyberbullying detection www.ijacsa.thesai.org tasks. The study in [12] introduced an LSTM-CNN hybrid model designed to analyze textual content from social media posts, achieving notable success in identifying instances of cyberbullying. This hybrid architecture leverages the temporal dynamics captured by LSTM units along with the spatial features extracted by CNN layers, enhancing the model's ability to capture nuanced patterns indicative of cyberbullying behavior.…”

Deteksi Depresi Pengguna Twitter Indonesia Menggunakan LSTM-RNN

“…Kontribusi dan tujuan dari penelitian kami adalah untuk mengembangkan dan mengoptimalkan penelitian [12] menggunakan metode yang berbeda yakni LSTM-RNN dan mendeteksi depresi pada tweet twitter, Penelitian [13] Identifikasi komentar kasar di media sosial Indonesia, menggabungkan RNN-LSTM mendapatkan hasil yang tinggi, dimana Presisi, recall, dan F1-score 94%, 95% dan 94%, sehingga penggabungan LSTM-RNN pada penelitian ini dilakukan untuk mendapatkan hasil akurasi yang memuaskan. Dataset yang digunakan sama dengan penelitian sebelumnya, nantinya dalam penelitian ini akan mengimplementasikan beberapa eksperimen pada arsitektur model (misalnya, penyetelan hyperparameter) untuk Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI | 322 mendapatkan hasil kinerja setinggi mungkin dan untuk menghindari overfits dan underfits.…”

Optimization of support vector machine with cubic kernel function to detect cyberbullying in social networks

“…So that arises encouragement from various groups and individuals on social networking [9]. This accelerates the delivery of bladder to become cyberbullying, where cyberbullying is an abuse of the use of the internet network by harassing, humiliating, threatening, and insulting others with digital trace recording [10].…”