DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform

IEEE Access

Mufeed Ahmed Naji Saif¹  Hasib Daowd Esmail Al-Ariki²  Belal Abdullah Hezam Murshed³  Suresha Mallappa³  Jemal Abawajy⁴ 

[1] Department of Computer Applications, Sri Jayachamarajendra College of Engineering, (Affiliated to VTU), JSS TI Campus, Mysore, Karnataka, India;Department of Computer Networks and Distributed Systems, Al Saeed faculty for Engineering and Information Technology, Taiz University, Taiz, Yemen;Department of Studies in Computer Science, Mysore University, Mysore, Karnataka, India;School of Information Technology, Faculty of Science, Engineering and Built Environment, Deakin University, Geelong, VIC, Australia;

关键词: Cyber-bullying;    tweet classification;    Dolphin Echolocation algorithm;    Elman recurrent neural networks;    short text topic modeling;    cyberbullying detection;   

DOI  :  10.1109/ACCESS.2022.3153675

来源: DOAJ

【 摘 要 】

Cyberbullying (CB) has become increasingly prevalent in social media platforms. With the popularity and widespread use of social media by individuals of all ages, it is vital to make social media platforms safer from cyberbullying. This paper presents a hybrid deep learning model, called DEA-RNN, to detect CB on Twitter social media network. The proposed DEA-RNN model combines Elman type Recurrent Neural Networks (RNN) with an optimized Dolphin Echolocation Algorithm (DEA) for fine-tuning the Elman RNN’s parameters and reducing training time. We evaluated DEA-RNN thoroughly utilizing a dataset of 10000 tweets and compared its performance to those of state-of-the-art algorithms such as Bi-directional long short term memory (Bi-LSTM), RNN, SVM, Multinomial Naive Bayes (MNB), Random Forests (RF). The experimental results show that DEA-RNN was found to be superior in all the scenarios. It outperformed the considered existing approaches in detecting CB on Twitter platform. DEA-RNN was more efficient in scenario 3, where it has achieved an average of 90.45% accuracy, 89.52% precision, 88.98% recall, 89.25% F1-score, and 90.94% specificity.

【 授权许可】

Unknown