Gideon Mwendwa; Lokesh Chouhan; Ranjit Kolkar

Deep Ensemble Hybrid Model for Extremism Detection and Threat Inference in Counter-Terrorism Intelligence on Social Media

PDF (1269KB), PP.161-182

Views: 0 Downloads: 0

Author(s)

Gideon Mwendwa ^1,* Lokesh Chouhan ² Ranjit Kolkar ²

1. National Forensic Sciences University, School of Doctoral Studies and Research, 403401, Goa, India

2. National Forensic Sciences University, School of Cyber Security and Digital Forensics, 403401, Goa, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2026.04.09

Received: 9 Jan. 2026 / Revised: 25 Mar. 2026 / Accepted: 7 Jun. 2026 / Published: 8 Aug. 2026

Index Terms

Extremism, Shapley Additive exPlanations (SHAP), Hybrid Model, Machine Learning, Counter-terrorism

Abstract

Social media’s worldwide expansion over the past two decades has significantly altered the dissemination of extremist narratives, creating both challenges and opportunities for counterterrorism efforts. Addressing critical gaps in the detection and classification of extremist content on social media platforms, this research supports earlier-stage analytical assessment for law enforcement and security agencies. Using datasets from the publicly available Global Terrorism Database (GTD, n > 209,000 incidents) and a curated corpus of labeled tweets (n = 17,410), a hybrid framework integrating machine learning and deep learning models through a late-fusion stacking architecture is developed. The proposed ensemble leverages contextual indicators derived from historical terrorism data alongside linguistic and behavioral signals from social media content to distinguish extremist from non-extremist activity. Evaluated under strict temporal validation, the model achieves an accuracy of 98.52%, precision of 97.01%, recall of 99.66%, and an AUC of 0.92 under controlled experimental conditions. To address ethical and transparency considerations, Shapley Additive exPlanations (SHAP) are employed to enhance collectively indicate that integrating interpretability in automated decision-making. While the reported results reflect dataset-specific evaluation, the findings historical terrorism intelligence with temporally ordered social media analysis can support counterterrorism efforts by mitigating digital radicalization pathways and associated downstream physical security risks linked to terrorism and extremism through earlier analytical intervention.

Cite This Paper

Gideon Mwendwa, Lokesh Chouhan, Ranjit Kolkar, "Deep Ensemble Hybrid Model for Extremism Detection and Threat Inference in Counter-Terrorism Intelligence on Social Media", International Journal of Intelligent Systems and Applications(IJISA), Vol.18, No.4, pp.161-182, 2026. DOI:10.5815/ijisa.2026.04.09

Reference

[1]Ö. Sevdiren, "The crime of disseminating terrorism-related propaganda in Turkey: An 'exceptional' case for the concrete endangerment approach?", Criminal Law Forum, pp. 1–52, 2024.
[2]International Centre for Counter-Terrorism, "The radicalization (and counter-radicalization) potential of artificial intelligence", ICCT Publications, 2024.
[3]K. Zhaksylyk, B. Omarov, and S. Mussiraliyeva, "Review of violent extremism detection techniques on social media", in Proc. 16th Int. Conf. on Electronics Computer and Computation (ICECCO), pp. 1–5, 2021.
[4]M. Bolatbek, M. Sagynay, S. Mussiraliyeva, K. Baisylbayeva, and Z. Yeltay, "Kazakh language dataset for hate speech detection on social media text", in Proc. IEEE 9th Int. Conf. on Computational Intelligence and Applications (ICCIA), pp. 94–98, 2024.
[5]International Centre for Counter-Terrorism, "Exploitation of generative AI by terrorist groups", ICCT Publications, 2024.
[6]K. O. Ogutu and F. O. Nyagwara, "Critical analysis of status of counter-terrorism strategies in Manda, Lamu County, Kenya: A multifaceted examination of HUMINT and SIGINT", Humanities and Social Sciences, vol. 13, no. 1, pp. 80–90, 2024.
[7]V. Dragos and Y. Constable, "Comparison of classification techniques for extremism detection in French social media", in Proc. 26th Int. Conf. on Information Fusion (FUSION), pp. 1–6, 2023.
[8]M.-A. Richardson, "Predicting violent extremism with machine learning: A scoping review", SN Computer Science, vol. 5, no. 1, p. 16, 2023.
[9]M. Gaikwad, S. Ahirrao, S. Phansalkar, and K. Kotecha, "Online extremism detection: A systematic literature review with emphasis on datasets, classification techniques, validation methods, and tools", IEEE Access, vol. 9, pp. 48364–48404, 2021.
[10]G. Mwendwa, L. Chouhan, F. Etyang, N. Mandela, and U. Gift, "Combating terrorism: Detecting and analyzing extremist content on X (formerly Twitter)", in Proc. 3rd Edition of IEEE Delhi Section Flagship Conf. (DELCON), pp. 1–7, 2024.
[11]M. Xi, L. Nie, and J. Song, "Research on urban anti-terrorism intelligence perception system from the perspective of Internet of Things application", Int. J. Electrical Engineering & Education, vol. 58, no. 2, pp. 248–257, 2021.
[12]M. Gaikwad, S. Ahirrao, K. Kotecha, and A. Abraham, "Multi-ideology multi-class extremism classification using deep learning techniques", IEEE Access, vol. 10, pp. 104829–104843, 2022.
[13]J. Scanlon, "Automatic detection and forecasting of violent extremist cyber-recruitment", M.Sc. thesis, University of Virginia, 2014.
[14]F. Sufi, "A new social media-driven cyber threat intelligence", Electronics, vol. 12, no. 5, p. 1242, 2023.
[15]S. K. Habibabadi, C. Palmer, G. L. Dimaguila, M. Javed, H. J. Clothier, and J. Buttery, "Automated social media surveillance for detection of vaccine safety signals: A validation study", Applied Clinical Informatics, vol. 14, no. 1, pp. 1–10, 2023.
[16]A. K. Yee, "Construct validity in automated counterterrorism analysis", Philosophy of Science, pp. 1–18, 2024.
[17]S. Aldera, A. Emam, M. Al-Qurishi, M. Alrubaian, and A. Alothaim, "Exploratory data analysis and classification of a new Arabic online extremism dataset", IEEE Access, vol. 9, pp. 161613–161626, 2021.
[18]J. Bartlett and L. Reynolds, "The state-of-the-art 2015: A literature review of social media intelligence capabilities for counter-terrorism", Technical Report, Demos, 2015.
[19]J. Torregrosa, G. Bello-Orgaz, E. Martínez-Cámara, J. Del Ser, and D. Camacho, "A survey on extremism analysis using natural language processing: Definitions, literature review, trends and challenges", Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 8, pp. 9869–9905, 2023.
[20]F. A. Khan, G. Li, A. N. Khan, Q. W. Khan, M. Hadjouni, and H. Elmannai, "AI-driven counter-terrorism: Enhancing global security through advanced predictive analytics", IEEE Access, vol. 11, pp. 135864–135879, 2023.
[21]E. Rodilosso, "Filter bubbles and the unfeeling: How AI for social media can foster extremism and polarization", Philosophy & Technology, vol. 37, no. 2, p. 71, 2024.
[22]I. Kim, W. M. Pottenger, and V. Behe, "Deep learning-based named entity recognition using automatic labeling of the global terrorism database", in Proc. IEEE Int. Symp. on Technologies for Homeland Security (HST), pp. 1–6, 2018.
[23]S. Mussiraliyeva, B. Omarov, P. Yoo, and M. Bolatbek, "Applying machine learning techniques for religious extremism detection on online user contents", Computers, Materials & Continua, vol. 70, no. 1, pp. 915–934, 2022.
[24]A. S. Al-Fallooji and A. Al-Azawei, "Predicting users' personality on social media: A comparative study of different machine learning techniques", Karbala Int. J. of Modern Science, vol. 8, no. 4, p. 5, 2022.
[25]A. Falzon and J. Azzopardi, "TerrorMine: Automatically identifying the group behind a terrorist attack", in Proc. 14th Int. Joint Conf. on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K–KDIR), pp. 221–228, 2022.
[26]N. Rawat, S. Chauhan, and L. K. Awasthi, "Deep learning approaches for predicting mental states through tweet analysis", in Proc. 5th Int. Conf. on Innovative Trends in Information Technology (ICITIIT), pp. 1–6, 2024.
[27]A. Z. Rozo, D. Díaz-López, J. Pastor-Galindo, F. Gómez Mármol, and U. Karabiyik, "An NLP-based framework to spot extremist networks in social media", Complexity, vol. 2024, no. 1, p. 3380488, 2024.
[28]E. Shadadi, S. Kouser, L. Alamer, and P. Whig, "Novel approach of predicting human sentiment using deep learning", Journal of Computer Science and Engineering, vol. 3, no. 2, 2022.
[29]R. K. Mishra, S. Urolagin, J. A. A. Jothi, A. S. Neogi, and N. Nawaz, "Deep learning-based sentiment analysis and topic modeling on tourism during COVID-19 pandemic", Frontiers in Computer Science, vol. 3, 2021.
[30]F. Malcolm, "Analysing extremism", Ethical Theory and Moral Practice, vol. 26, no. 2, pp. 321–327, 2023.
[31]S. Aslan, "A novel TCNN-Bi-LSTM deep learning model for predicting sentiments of tweets about COVID-19 vaccines", Concurrency and Computation: Practice and Experience, vol. 34, no. 28, e7387, 2022.
[32]M. Abdalsalam, C. Li, A. Dahou, and N. Kryvinska, "Terrorism attack classification using machine learning: Effectiveness of textual features extracted from GTD dataset", CMES–Computer Modeling in Engineering & Sciences, vol. 138, no. 2, 2024.
[33]M. Adnan and M. Rafi, "Extracting patterns from global terrorist dataset using co-clustering approach", Journal of Independent Studies and Research, vol. 13, no. 1, p. 7, 2015.
[34]United Nations Counter-Terrorism Centre and United Nations Interregional Crime and Justice Research Institute, "Countering terrorism online with artificial intelligence", Technical Report, United Nations, 2021.
[35]A. Anil, S. R. Singh, and R. Sarmah, "Personalised PageRank as a method of exploiting heterogeneous network for counter terrorism and homeland security", in Proc. IEEE/WIC/ACM Int. Conf. on Web Intelligence, pp. 327–334, 2016.
[36]G. Mwendwa, A. Nagpal, S. Garg, L. Chouhan, and N. Mandela, "Graph neural networks for temporal terrorist network analysis and multi-relational threat prediction", International Journal of Information Technology, 2025.
[37]T. Xia and Y. Gu, "Building terrorist knowledge graph from global terrorism database and Wikipedia", in Proc. IEEE Int. Conf. on Intelligence and Security Informatics (ISI), pp. 194–196, 2019.
[38]R. Q. Al-Fayez, M. Al-Tawil, B. Abu-Salih, and Z. Eyadat, "GTDOnto: An ontology for organizing and modeling knowledge about global terrorism", Big Data and Cognitive Computing, vol. 7, no. 1, p. 24, 2023.
[39]N. V. Khokhlov and A. V. Korotaev, "Internet and terrorist activity in countries with different political regimes: A quantitative analysis", Politeia, vol. 97, no. 2, pp. 67–86, 2020.
[40]S. O. Uche, N. Tsopzé, and D. U. Ebem, "Data mining approach to counterterrorism", Advances in Multidisciplinary & Scientific Research, vol. 11, no. 2, pp. 77–90, 2020.
[41]G. Mwendwa, L. Chouhan, H. A. Elsayed, A. Mehaney, W. Al Zoubi, J. Wekalao, and Y. Prabhu, "Deciphering terrorist attributions: A global terrorism data-driven comparison of machine learning models", Social Network Analysis and Mining, vol. 15, no. 1, p. 99, 2025.
[42]United Nations Interregional Crime and Justice Research Institute (UNICRI), "Countering terrorism online with artificial intelligence: An overview for South Asia and South-East Asia", UNICRI Publications, 2024.
[43]R. Frankenberger, R. Baur, M. Rieger-Ladich, J. Schmid, B. Stauber, A. Thiel, and T. Thomas, "Researching far right extremism: A transdisciplinary, lifeworld, and political culture perspective", Zeitschrift für Vergleichende Politikwissenschaft, vol. 17, no. 3, pp. 275–295, 2023.
[44]G. M. Ndungi, L. Chouhan, and F. Etyang, "Systematic literature review on the synergy of social media forensics and mobile forensics in the investigation of cybercrimes", in Advances in Data-Driven Computing and Intelligent Systems, Springer Nature Singapore, pp. 503–520, 2024.
[45]E. Jesse, "Left-wing extremism in Germany", in The Palgrave Handbook of Left-Wing Extremism, Springer International Publishing, pp. 173–191, 2023.
[46]Y. Tian, R. Fan, X. Ding, X. Zhang, and T. Gan, "Predicting rumor retweeting behavior of social media users in public emergencies", IEEE Access, vol. 8, pp. 87121–87132, 2020.
[47]N. Sharma, I. Batra, and A. Malik, "Comparative study of malware detection using hybrid deep learning techniques", in Proc. ASU Int. Conf. on Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), pp. 1260–1266, 2024.
[48]C. Orellana-Rodriguez and M. T. Keane, "Modeling and predicting news consumption on Twitter", in Proc. 26th Conf. on User Modeling, Adaptation and Personalization, pp. 321–329, 2018.
[49]R. Chellappa, S. Theodoridis, and A. van Schaik, "Advances in machine learning and deep neural networks", Proceedings of the IEEE, vol. 109, no. 5, pp. 607–611, 2021.
[50]Digital Watch Observatory, "AI and violent extremism – trends in 2025", 2025. Available: https://dig.watch/topics/violent-extremism (accessed Jan. 2025).
[51]L. Ritter, M. A. Weber, R. Witt, V. Profes, J. P. Singh, J. Endrass, and A. Rossegger, "Improving violent extremism risk communication among German police agencies: A survey of federal and state threat managers", Journal of Police and Criminal Psychology, pp. 1–10, 2023.
[52]D. Karanatsiou, P. Sermpezis, D. Gruda, K. Kafetsios, I. Dimitriadis, and A. Vakali, "My tweets bring all the traits to the yard: Predicting personality and relational traits in online social networks", ACM Transactions on the Web, vol. 16, no. 2, 2022.
[53]S. Mussiraliyeva, K. Baisylbayeva, M. Bolatbek, and Z. Yeltay, "Decoding ideology: Machine learning-based detection of extremist content", in Proc. Int. Conf. on Intelligent Computing, Communication, Networking and Services (ICCNS), pp. 114–120, 2024.
[54]P. V. Reddy, S. Sanku, T. Akhilsai, and A. Gayatri, "CNN based criminal face identification system using video surveillance", SSRN Electronic Journal, 2024.

International Journal of Intelligent Systems and Applications (IJISA)