Cyberbullying Detection on Social Media Using Stacking Ensemble Learning and Enhanced BERT

被引:7
作者
Muneer, Amgad [1 ,2 ]
Alwadain, Ayed [3 ]
Ragab, Mohammed Gamal [2 ]
Alqushaibi, Alawi [2 ]
机构
[1] Univ Texas MD Anderson Canc Ctr, Dept Imaging Phys, Houston, TX 77030 USA
[2] Univ Teknol PETRONAS, Dept Comp & Informat Sci, Seri Iskandar 32610, Malaysia
[3] King Saud Univ, Community Coll, Comp Sci Dept, Riyadh 145111, Saudi Arabia
关键词
cyberbullying detection; ensemble learning; stacked; continuous bag of words; word2vec; Twitter; X platform; Facebook; social media; natural language processing;
D O I
10.3390/info14080467
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The prevalence of cyberbullying on Social Media (SM) platforms has become a significant concern for individuals, organizations, and society as a whole. The early detection and intervention of cyberbullying on social media are critical to mitigating its harmful effects. In recent years, ensemble learning has shown promising results for detecting cyberbullying on social media. This paper presents an ensemble stacking learning approach for detecting cyberbullying on Twitter using a combination of Deep Neural Network methods (DNNs). It also introduces BERT-M, a modified BERT model. The dataset used in this study was collected from Twitter and preprocessed to remove irrelevant information. The feature extraction process involved utilizing word2vec with Continuous Bag of Words (CBOW) to form the weights in the embedding layer. These features were then fed into a convolutional and pooling mechanism, effectively reducing their dimensionality, and capturing the position-invariant characteristics of the offensive words. The validation of the proposed stacked model and BERT-M was performed using well-known model evaluation measures. The stacked model achieved an F1-score of 0.964, precision of 0.950, recall of 0.92 and the detection time reported was 3 min, which surpasses the previously reported accuracy and speed scores for all known NLP detectors of cyberbullying, including standard BERT and BERT-M. The results of the experiment showed that the stacking ensemble learning approach achieved an accuracy of 97.4% in detecting cyberbullying on Twitter dataset and 90.97% on combined Twitter and Facebook dataset. The results demonstrate the effectiveness of the proposed stacking ensemble learning approach in detecting cyberbullying on SM and highlight the importance of combining multiple models for improved performance.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Transformer models for text-based emotion detection: a review of BERT-based approaches
    Acheampong, Francisca Adoma
    Nunoo-Mensah, Henry
    Chen, Wenyu
    [J]. ARTIFICIAL INTELLIGENCE REVIEW, 2021, 54 (08) : 5789 - 5829
  • [2] Aind A. T., 2020, 2020 INT C EMERGING, P1, DOI [10.1109/INCET49848.2020.9154092, DOI 10.1109/INCET49848.2020.9154092]
  • [3] Al-Ajlan MA, 2018, 2018 21ST SAUDI COMPUTER SOCIETY NATIONAL COMPUTER CONFERENCE (NCC)
  • [4] Enhanced Weight-Optimized Recurrent Neural Networks Based on Sine Cosine Algorithm for Wave Height Prediction
    Alqushaibi, Alawi
    Abdulkadir, Said Jadid
    Rais, Helmi Md
    Al-Tashi, Qasem
    Ragab, Mohammed G.
    Alhussian, Hitham
    [J]. JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2021, 9 (05)
  • [5] Arisanty M., 2022, Jurnal Kajian Komunikasi, V10, P215, DOI [10.24198/jkk.v10i2.39876, DOI 10.24198/JKK.V10I2.39876]
  • [6] Cyberbullying among young adults in Malaysia: The roles of gender, age and Internet frequency
    Balakrishnan, Vimala
    [J]. COMPUTERS IN HUMAN BEHAVIOR, 2015, 46 : 149 - 157
  • [7] Banerjee V, 2019, INT CONF ADVAN COMPU, P604, DOI [10.1109/ICACCS.2019.8728378, 10.1109/icaccs.2019.8728378]
  • [8] Ensemble learning-based approach for improving generalization capability of machine reading comprehension systems
    Baradaran, Razieh
    Amirkhani, Hossein
    [J]. NEUROCOMPUTING, 2021, 466 : 229 - 242
  • [9] Cyberbullying detection: Utilizing social media features
    Bozyigit, Alican
    Utku, Semih
    Nasibov, Efendi
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2021, 179
  • [10] The Use of Social Media in Children and Adolescents: Scoping Review on the Potential Risks
    Bozzola, Elena
    Spina, Giulia
    Agostiniani, Rino
    Barni, Sarah
    Russo, Rocco
    Scarpato, Elena
    Di Mauro, Antonio
    Di Stefano, Antonella Vita
    Caruso, Cinthia
    Corsello, Giovanni
    Staiano, Annamaria
    [J]. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2022, 19 (16)