Citation :

D. Jagannathan, N. V. Balaji, "MSCT-CDMO-TFT: A Hybrid Deep Learning Framework for Sentiment Analysis and Cyberbullying Detection," International Journal of Electronics and Communication Engineering, vol. 13, no. 5, pp. 151-170, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I5P114

Abstract

Cyberbullying has proliferated, particularly among youngsters, due to the expansion of digital platforms and technological advancements. Cyberbullying has emerged as a worldwide concern on social media sites, when individuals transition between networks to avoid detection. This study proposes a Cyberbullying Detection (CBD) framework that is trained using sentiment, emotional, and contextual features. The proposed CBD framework is developed using a Multi-Scale Contextual Transformer-Chaotic Dwarf Mongoose Optimizer-Temporal Fusion Transformer (MSCT-CDMO-TFT) model. The MSCT-CDMO-TFT model is evaluated with IMDB, Yelp Polarity, and Cyberbullying Classification datasets. The MSCT algorithm is applied for extracting multi-level contextual features, which enabled the model to learn local semantic patterns together with global contextual dependencies from complex textual data that contained various noise elements. The application of CDMO in feature selection led to a reduction of redundant features while maintaining essential discriminative features, which resulted in improved performance and classification accuracy. The framework also applied a TFT classifier that successfully executed temporal and contextual interaction modelling through its gated residual learning and attention mechanism capabilities. The proposed model demonstrates superior results on the cyberbullying classification dataset with 98.49% accuracy, 98.35% recall, 98.28% precision, and a 98.40% F1-score. The MSCT-CDMO-TFT model achieves better performance than all other current methods discussed in this study.

Keywords

Cyberbullying Detection, Cdmo, Multi-Scale Contextual Transformer, Temporal Fusion Transformer, Sentiment Classification.

References

1. Mohammed Hussein Obaida, Saleh Mesbah Elkaffas, and Shawkat Kamal Guirguis, “Deep Learning Algorithm for Cyber-Bulling Detections in Social Media Platform,” IEEE Access, vol. 12, pp. 76901-76908, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Jana Lekscha, and Milad Mirbabaie, “How to Analyze Cyberbullying on Social Media Platform: A Systematic Literatures Review in Information System,” i-com, vol. 24, no. 2, pp. 385-405, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Vidhushavarshini Suresh Kumar et al., “A Comprehensive Review of TriBERT-X: A Concatenated Transformers Approach for Explainable Cyberbullying Detections on Twitter,” International Conferences on Intelligent System and Digital Transformations (ICISD), pp. 77-89, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Daniyar Sultan et al., “A Review of Machine Learning Techniques in Cyberbullying Detection,” Computers, Material & Continua, vol. 74, no. 3, pp. 5625-5640, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Bedour Alrashidi et al., “A Review on Abusive Contents Automatic Detections: Approaches, Challenge and Opportunities,” PeerJ Computer Sciences, vol. 8, pp. 1-32, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Malliga Subramanian et al., “A Survey on Hate Speech Detection and Sentiment Analysis using Machine Learning and Deep Learning Models,” Alexandria Engineering Journal, vol. 80, pp. 110-121, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Swapnil Sanjaykumar Mane, Suman Kundu, and Rajesh Sharma, “A Survey on Online Aggressions: Contents Detections and Behavioural Analysis on Social Medias,” ACM Computing Survey, vol. 57, no. 7, pp. 1-36, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Biodoumoye George Bokolo, and Qingzhong Liu, “Artificial Intelligences in Social Media Forensic: A Comprehensive Survey and Analysis,” Electronics, vol. 13, no. 9, pp. 1-24, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Hooayda Allwaibed et al., “Cyberbullying Detections Approaches for Arabic Text: A Systematic Literatures Review,” Frontiers in Artificial Intelligences, vol. 8, pp. 1-13, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Golam Md Mohiuddin, Md Shohel Sayeed, and Ong Lee Yeng, “Deep Learning Model for Culturally Aware Cyberbullying Detections in Muslims Societies: A Systematic Review,” Discover Artificial Intelligence, vol. 5, pp. 1-38, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Anthony Obogo Otiko et al., “A Hybrid Machine Learnings Approach for Multi-Class Cyberbullying Detections,” SSRN, pp. 1-10, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Lida Ketsbaia et al., “A Multi-Stages Machine Learnings and Fuzzy Approach to Cyber-Hates Detections,” IEEE Access, vol. 11, pp. 56046-56065, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Krishanu Maity, Abhishek Kumar, and Sriparna Saha, “A Multitask Multimodal Framework for Sentiment and Emotion-Aided Cyberbullying Detection,” IEEE Internet Computing, vol. 26, no. 4, pp. 68-78, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Snigdha Luthra, Rakesh Kumar, and Meenu Gupta, “A Novel Hybrid Model Based on Sentiment Analysis Using Community Guided Link Prediction for Connecting People With Similar Interest,” IEEE Access, vol. 12, pp. 139435-1394455, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Atika Gupta, Priya Matta, and Bhasker Pant, “An Integrated Users Matching Framework for Cross-Platforms Cyberbullying Detections,” Discover Computing, vol. 28, pp. 1-24, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
16. O. Ayodeji et al., “CBDS-ConvNet: A Cyber-Bullying Detection Model using Convolutional Neural Network,” Communications on Applied Electronics, vol. 7, no. 40, pp. 11-21, 2025.
    [Google Scholar] [Publisher Link]
17. Azhi Faraj, and Semih Utku, “Comparative Analysis of Words Embedding for Multiclass Cyberbullying Detections,” UHD Journal of Sciences and Technology, vol. 8, no. 1, pp. 55-63, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Mohammed Al-Hashedi et al., “Cyberbullying Detection Based on Emotion,” IEEE Access, vol. 11, pp. 53907-53918, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Muhammad Mubeen et al., “Cyberbullying-Related Automated Hate Speech Detection on Social Media Platforms Using Stack Ensemble Classification Method,” International Journal of Computational Intelligences System, vol. 18, pp. 1-24, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Amr Mohamed El Koshiry et al., “Detecting Cyberbullying using Deep Learnings Technique: A Pre-Trained Glove and Focal Loss Techniques,” PeerJ Computer Science, vol. 10, pp. 1-33, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Raghu Dhumpati et al., “Enhancing Sarcasm Detection in Sentiment Analysis for Cyberspace Safety Using Advanced Deep Learning Techniques,” Scientific Report, vol. 15, pp. 1-19, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Ravuri Daniel et al., “Ensemble Learning with Tournament Selected Glowworm Swarm Optimization Algorithm for Cyberbullying Detection on Social Media,” IEEE Access, vol. 11, pp. 123392-123400, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Siti Ernawati, Frieyadie Frieyadie, and Eka Rini Yulia, “HyVADSVM: Hybrid VADER-SVM and GridSearchCV Optimization for Enhancing Cyberbullying Detection,” Journal of Robotic and Controls, vol. 6, no. 1, pp. 101-113, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Arwa A. Jamjoom et al., “RoBERTaNET: Enhanced RoBERTa Transformer Based Model for Cyberbullying Detection with GloVe Features,” IEEE Access, vol. 12, pp. 58950-58959, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Adamu Philipo et al., “Sentiment-Enhanced Cyberbullying Detection Models on Social Media Platforms,” ACM Transactions on the Web, vol. 20, no. 1, pp. 1-26, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Zeeshan Shaukat et al., “Sentiment Analysis on IMDB Using Lexicon and Neural Networks,” SN Applied Science, vol. 2, pp. 1-10, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Mujiono Sadikin, and Abi Fauzan, “Evaluation of Machine Learning Approach for Sentiment Analysis using Yelp Dataset,” European Journal of Electrical Engineering and Computer Sciences, vol. 7, no. 6, pp. 58-64, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Meruert Yerekesheva et al., “A Hybrid BERT-CNN with Multihead Self-Attention for Automated Cyberbullying Detection,” Engineering, Technology & Applied Sciences Research, vol. 16, no. 1, pp. 30716-30724, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Naga Surekha Jonnala et al., “Leveraging Hybrid Models for Accurate Sentiments Analysis of Twitter Data,” Scientific Report, vol. 15, pp. 1-9, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Ziyang He, and Ziyi Wang, “Multi-Scale Contextual Transformer for MRI Super-Resolution,” 2024 5^th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), Wenzhou, China, pp. 517-520, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
31. Cheng da et al., “MCATD: Multi-Scale Contextual Attention Transformer Diffusion for Unsupervised Low-Light Image Enhancement,” IEEE Access, vol. 13, pp. 97348-97363, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
32. Mohammed Abdelrazek, Mohamed Abd Elaziz, and A. H. El-Baz, “CDMO: Chaotic Dwarf Mongoose Optimization Algorithm for Feature Selection,” Scientific Reports, vol. 14, pp. 1-18, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
33. Bryan Lim et al., “Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting,” International Journal of Forecasting, vol. 37, no. 4, pp. 1748-1764, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
34. Iyan E. Mulia et al., “Multi-Horizon Prediction of Tropical Cyclone Intensity and its Interpretability with Temporal Fusion Transformer,” Scientific Reports, vol. 15, pp. 1-16, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]