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

被引:35
作者
Murshed, Belal Abdullah Hezam [1 ,2 ]
Abawajy, Jemal [3 ]
Mallappa, Suresha [1 ]
Saif, Mufeed Ahmed Naji [4 ]
Al-Ariki, Hasib Daowd Esmail [5 ,6 ]
机构
[1] Mysore Univ, Dept Studies Comp Sci, Mysore 570006, Karnataka, India
[2] Amran Univ, Coll Engn & IT, Dept Comp Sci, Amran, Yemen
[3] Deakin Univ, Fac Sci Engn & Built Environm, Sch Informat Technol, Geelong, Vic 3220, Australia
[4] VTU, Dept Comp Applicat, Sri Jayachamarajendra Coll Engn, JSSTI Campus, Mysore 570006, Karnataka, India
[5] Taiz Univ, Al Saeed Fac EngineeringandInformat Technol, Dept Comp Networks & Distributed Syst, Taizi, Yemen
[6] Sanaa Community Coll, Dept Comp Networks Engn & Technol, Sanaa, Yemen
关键词
Cyberbullying; Blogs; Feature extraction; Support vector machines; Recurrent neural networks; Training; Numerical models; Cyber-bullying; tweet classification; Dolphin Echolocation algorithm; Elman recurrent neural networks; short text topic modeling; cyberbullying detection; social media;
D O I
10.1109/ACCESS.2022.3153675
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
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.
引用
收藏
页码:25857 / 25871
页数:15
相关论文
共 62 条
  • [1] Feature selection techniques in the context of big data: taxonomy and analysis
    Abdulwahab, Hudhaifa Mohammed
    Ajitha, S.
    Saif, Mufeed Ahmed Naji
    [J]. APPLIED INTELLIGENCE, 2022, 52 (12) : 13568 - 13613
  • [2] Agarwal A., 2020, NEURAL INFORM PROCES, P113, DOI DOI 10.1007/978-3-030-63823-8_14
  • [3] Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platforms
    Agrawal, Sweta
    Awekar, Amit
    [J]. ADVANCES IN INFORMATION RETRIEVAL (ECIR 2018), 2018, 10772 : 141 - 153
  • [4] Abusive language detection from social media comments using conventional machine learning and deep learning approaches (Apr, 10.1007/S00530-021-00784-8, 2021)
    Akhter, Muhammad Pervez
    Jiangbin, Zheng
    Naqvi, Irfan Raza
    AbdelMajeed, Mohammed
    Zia, Tehseen
    [J]. MULTIMEDIA SYSTEMS, 2023, 29 (01) : 451 - 451
  • [5] Al-Ajlan MA, 2018, 2018 21ST SAUDI COMPUTER SOCIETY NATIONAL COMPUTER CONFERENCE (NCC)
  • [6] Cybercrime detection in online communications: The experimental case of cyberbullying detection in the Twitter network
    Al-garadr, Mohammed Ali
    Varathan, Kasturi Dewi
    Ravana, Sri Devi
    [J]. COMPUTERS IN HUMAN BEHAVIOR, 2016, 63 : 433 - 443
  • [7] Detection of hate speech in Arabic tweets using deep learning
    Al-Hassan, Areej
    Al-Dossari, Hmood
    [J]. MULTIMEDIA SYSTEMS, 2022, 28 (06) : 1963 - 1974
  • [8] Alam Kazi Saeed, 2021, Proceedings of the Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV 2020), P710, DOI 10.1109/ICICV50876.2021.9388499
  • [9] Anuprathibha T., 2019, Int. J. Recent Technol. Eng, V8, P648, DOI [10.35940/ijrte.B2629.098319, DOI 10.35940/IJRTE.B2629.098319]
  • [10] Anuprathibha T., 2019, INT J INNOV TECHNOL, V8, P2049, DOI [10.35940/ijitee.J9317.0881019, DOI 10.35940/IJITEE.J9317.0881019]