Leveraging Artificial Intelligence and Machine Learning in Online Threat Detection
DOI:
https://doi.org/10.26438/ijcse/v13i2.4956Keywords:
Artificial Intelligence (AI), Online Threat Detection, Machine Learning (ML), Large Language Models (LLMs)Abstract
This literature review examines the roles of artificial intelligence (AI), machine learning (ML), and large language models (LLMs) in identifying and interpreting online threats. As AI and ML technologies advance, their use in analyzing vast online data for potential threats has grown significantly. The review systematically evaluates current methodologies for detecting and assessing threats, particularly in social media and online forums, which are both information hubs and sources of harmful content. Key findings highlight the effectiveness of BERT-based models in hate speech detection across languages and platforms, emphasizing their interpretability and transparency advantages over traditional neural networks. Models like GPT-4 further expand threat identification capabilities, detecting cyber threats and abusive language, with implications for public safety and mental health monitoring. Challenges remain, particularly in handling noisy, diverse, and imbalanced social media datasets. Domain-specific word embeddings and ensemble techniques, such as combining BERT with TextCNN and BiLSTM, show promise in improving detection accuracy in complex data environments. The review advocates for continued focus on hybrid and ensemble models to address data complexities and calls for future research to enhance model transparency and address ethical concerns like data privacy. Given the rise in digital communication, real-time threat detection is crucial for public safety, national security, and violence prevention. This review consolidates findings on the efficacy of AI and ML in detecting online threats, identifies recurring challenges, and outlines research gaps to guide future advancements. By synthesizing recent studies, it provides a structured analysis of the current capabilities and limitations of AI and ML in online threat monitoring, contributing to a foundational understanding of how these technologies can evolve to enhance societal safety.
References
[1] Adewumi, T., Sabry, S. S., Abid, N., Liwicki, F., & Liwicki, M., T5 for Hate Speech, Augmented Data, and Ensemble. Sci, Vol.5, Issue.4, pp.3-7, 2023. https://doi.org/10.3390/sci5040037
[2] Chakraborty, P., & Seddiqui, Md. H., Threat and Abusive Language Detection on Social Media in Bengali Language. 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), pp.1–6, 2019. https://doi.org/10.1109/ICASERT.2019.8934609
[3] Coppersmith, G., Leary, R., Crutchley, P., & Fine, A., Natural Language Processing of Social Media as Screening for Suicide Risk. Biomedical Informatics Insights, 10, 2018. https://doi.org/10.1177/1178222618792860
[4] Dehingia, N., McAuley, J., McDougal, L., Reed, E., Silverman, J. G., Urada, L., & Raj, A., Violence against women on Twitter in India: Testing a taxonomy for online misogyny and measuring its prevalence during COVID-19. PLOS ONE, Vol.18, Issue.10, pp.e0292121, 2023. https://doi.org/10.1371/journal.pone.0292121
[5] Elzayady, H., S. Mohamed, M., M. Badran, K., & I. Salama, G., Detecting Arabic textual threats in social media using artificial intelligence: An overview. Indonesian Journal of Electrical Engineering and Computer Science, Vol.25, Issue.3, pp.1712, 2022. https://doi.org/10.11591/ijeecs.v25.i3.pp1712-1722
[6] Faraj, A., & Utku, S., Comparative Analysis of Word Embeddings for Multiclass Cyberbullying Detection. UHD Journal of Science and Technology, Vol.8, Issue.1, pp.55–63, 2024. https://doi.org/10.21928/uhdjst.v8n1y2024.pp55-63
[7] Huang, Y., Song, R., Giunchiglia, F., & Xu, H., A Multitask Learning Framework for Abuse Detection and Emotion Classification. Algorithms, Vol.15, Issue.4, pp.1-16, 2022. https://doi.org/10.3390/a15040116
[8] Husain, F. A., Arabic Offensive Language Detection in Social Media. George Mason University, 2021.
[9] Kulkarni, V., Baghwat, V., Patli, A., Kumari, S., & Deep Kour, S., A System to Identify Threats on Social Media Conversations and Providing Preliminary Legal Actions. International Journal of Research and Analytical Reviews, Vol.10, Issue.4, pp.338–342, 2023.
[10] Kwon, T., & Kim, C., Efficacy of Utilizing Large Language Models to Detect Public Threat Posted Online, 2023.
[11] Manias, G., Mavrogiorgou, A., Kiourtis, A., Symvoulidis, C., & Kyriazis, D., Multilingual text categorization and sentiment analysis: a comparative analysis of the utilization of multilingual approaches for classifying twitter data. Neural Computing and Applications, Vol.35, Issue.29, pp.21415–21431, 2023. https://doi.org/10.1007/s00521-023-08629-3
[12] McKeever, S., Keegan, B., & Quieroz, A., Detecting Hacker Threats: Performance of Word and Sentence Embedding Models in Identifying Hacker Communications. AICS 2019 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science, 2020.
[13] Mnassri, K., Farahbakhsh, R., & Crespi, N., Multilingual Hate Speech Detection: A Semi-Supervised Generative Adversarial Approach. Entropy, Vol.26, Issue.4, p.344, 2024. https://doi.org/10.3390/e26040344
[14] Modha, S., Majumder, P., & Mandl, T., An empirical evaluation of text representation schemes to filter the social media stream. Journal of Experimental & Theoretical Artificial Intelligence, Vol.34, Issue.3, pp.499–525, 2022. https://doi.org/10.1080/0952813X.2021.1907792
[15] Mohamed, M. S., Elzayady, H., Badran, K. M., & Salama, G. I., An efficient approach for data-imbalanced hate speech detection in Arabic social media. Journal of Intelligent & Fuzzy Systems, Vol.45, Issue.4, pp.6381–6390, 2023. https://doi.org/10.3233/JIFS-231151
[16] Monnar, A. A., Perez Rojas, J., & Labra, B. P., Cross-lingual hate speech detection using domain-specific word embeddings. PLOS ONE, Vol.19, Issue.7, pp.e0306521, 2024. https://doi.org/10.1371/journal.pone.0306521
[17] Mossie, Z., & Wang, J.-H., Vulnerable community identification using hate speech detection on social media. Information Processing & Management, Vol.57, Issue.3, pp.102087, 2020. https://doi.org/10.1016/j.ipm.2019.102087
[18] Muneer, A., Alwadain, A., Ragab, M. G., & Alqushaibi, A., Cyberbullying Detection on Social Media Using Stacking Ensemble Learning and Enhanced BERT. Information, Vol.14, Issue.8, pp.467, 2023. https://doi.org/10.3390/info14080467
[19] Paraschiv, A., Ion, T. A., & Dascalu, M., Offensive Text Span Detection in Romanian Comments Using Large Language Models. Information, Vol.15, Issue.1, 8, 2023. https://doi.org/10.3390/info15010008
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
