An Approach to Early Detection of Sexual Predators in Virtual Conversations
Abstract
This work proposes the development of three distinct strategies for early detection of sexual predators in internet conversations between two people. Conversations from the PAN 2012 database and algorithms such as SVM, Random Forest, KNN and BERT will be used. It is expected to overcome the state of the art and prove that the "Distinguish Predatory and General Conversations" strategy can achieve better results than the others.
References
Escalante, H. J., Villatoro-Tello, E., Garza, S. E., López-Monroy, A. P., y Gómez, M. M., and Villaseñor-Pineda, L. (2017). Early detection of deception and aggressiveness using profile-based representations. Expert Systems with Applications, 89:99–111.
Fauzi, M. A. and Bours, P. (2020). Ensemble method for sexual predators identification in online chats. In 2020 8th International Workshop on Biometrics and Forensics, IWBF 2020 - Proceedings.
Inches, G. and Crestani, F. (2012). Overview of the international sexual predator identification competition at pan-2012. In CLEF
Kulsrud, H. (2019). Detection of cyber grooming during an online conversation. Master’s thesis, Norwegian University of Science and Technology
Olson, L. N., Daggs, J. L., Ellevold, B. L., and Rogers, T. K. K. (2007). Entrapping the innocent: Toward a theory of child sexual predators’ luring communication. Communication Theory, 17(3):231–251.
Pendar, N. (2007). Toward spotting the pedophile telling victim from predator in text chats. In International Conference on Semantic Computing (ICSC 2007), pages 235–241.
Villatoro-Tello, E., Juárez-González, A., Escalante, H. J., y Gómez, M. M., and Villaseñor-Pineda, L. (2012). A two-step approach for effective detection of misbehaving users in chats. In CLEF.