An Approach Utilizing Opinion Mining for the Detection of Radicalized Content in Social Media Platforms
Keywords:
Radical Content, Counter-terrorism, social networks, text analysis, Bayesian Regularization, correctnessAbstract
Through the widespread use of social broadcasting as a primary platform for message among individuals and communities, the potential for its misuse has grown significantly. One notable misuse is the dissemination of radical content, facilitated by the ease of sharing information across various networks. This poses a significant challenge for social media and security agencies, as they must sift through vast amounts of data to identify such content. The task becomes even more complex due to the lack of a clear difference between radical and non-radical material, especially as the volume of data continues to grow.
To address this issue, the study proposes an artificial intelligence-based method for detecting fundamental content. This method employs glossary learning to train a Bayesian Regularized Artificial Neural Network (ANN). Key recital metrics considered include the amount of iterations, processing time, and accuracy. The results demonstrate that the planned system achieves a organization accuracy of 97%, outperforming the previous benchmark of 89%.
Downloads
References
Agarwal, B., Poria, S., Mittal, N., Gelbukh, A., & Hussain, A. (2015). Concept-level sentiment analysis with dependency-based semantic parsing: A novel approach. Springer.
Akhgar, B., Tabatabayi, F., & Bayerl, P. S. (2014). Investigating radicalized individual profiles through fuzzy cognitive maps. Elsevier.
Al-Zewairi, M., & Naymat, G. (2017). Spotting the Islamist radical within Religious extremists profiling in the United States. Elsevier.
Ball, L. (2016). Automating social network analysis: A power tool for counter-terrorism. Springer.
Bobashev, G., Sageman, M., & Evans, A. L. (2019). Turning narrative descriptions of individual behaviour into network visualization and analysis: Example of terrorist group dynamics. IEEE.
Cherif, W., Madani, A., & Kissi, M. (2014). Integrating effective rules to improve Arabic text stemming. IEEE.
Drouin, J. (2014). Close- and distant-reading modernism: Network analysis, text mining, and teaching The Little Review. JSTOR.
Frank, R., Bouchard, M., Davies, G., & Mei, J. (2015). Spreading the message digitally: A look into extremist organizations' use of the internet. Springer.
Ishitaki, T., Obukata, R., & Oda, T. (2017). Application of deep recurrent neural networks for prediction of user behaviour in Tor networks. IEEE.
Ishitaki, T., Oda, T., & Barolli, L. (2015). Application of neural networks and Friedman test for user identification in Tor networks. IEEE.
Ishitaki, T., Oda, T., & Barolli, L. (2016). A neural network-based user identification for Tor networks: Data analysis using Friedman test. IEEE.
Johnston, A. H., & Weiss, G. M. (2017). Identifying Sunni extremist propaganda with deep learning. IEEE.
Kapitanov, A. I., Kapitanova, I. I., Troyanovskiy, V. M., Shangin, V. F., & Krylikov, N. O. (2022). Approach to automatic identification of terrorist and radical content in social networks message. IEEE.
Lara-Cabrera, R., & Gonzalez-Pardo, A. (2017). Extracting radicalization behavioral patterns from social network data. IEEE.
Li, Z., Sun, D., Li, B., Li, Z., & Li, A. (2018). Terrorist group behavior prediction by wavelet transform-based pattern recognition. Hindawi.
López-Sáncez, D., Revuelta, J., & de la Prieta, F. (2020). Towards the automatic identification and monitoring of radicalization activities in Twitter. IEEE.
Lourentzou, I., Morales, A., & Zhai, C. X. (2017). Text-based geolocation prediction of social media users with neural networks. IEEE.
Modupe, A., Olugbara, O. O., & Ojo, S. O. (2014). Filtering of mobile short messaging service communication using latent Dirichlet allocation with social network analysis. Springer.
Oda, T., Obukata, R., & Yamada, M. (2016). A neural network-based user identification for Tor networks: Comparison analysis of different activation functions using Friedman test. IEEE.
Sabbah, T., & Selamat, A. (2015). Hybridized feature set for accurate Arabic dark web pages classification. Springer.
Sabbah, T., & Selamat, A. (2015). Hybridized feature set for accurate content Arabic dark web pages classification. ResearchGate.
Sabbah, T., Selamat, A., Selamat, M. H., Ibrahim, R., & Fujita, H. (2016). Hybridized term-weighting method for dark web classification. Elsevier.
Scrivens, R., & Frank, R. (2016). Sentiment-based classification of radical text on the web. IEEE.
Tundis, A., Bhatia, G., & Jain, A. (2018). Supporting the identification and the assessment of suspicious users on Twitter social media. IEEE.
Wadhwa, P., & Bhatia, M. P. S. (2015). Tracking online radicalization using investigative data mining. IEEE.
Yucel, C., & Koltuksuz, A. (2014). An annotated bibliographical survey on cyber intelligence for cyber intelligence officers. JSTOR.
