Identifying Sexual Predators in Chats Using SVM and Feature Ensemble
Abstract
Cyber grooming is a compelling problem worldwide nowadays since people spend most of their time online. All of the reports strongly suggested that it becomes very urgent to tackle the online child grooming problem in order to protect children from sexual exploitation. Automatic sexual predator identification can be a promising solution to this issue since the number of online conversations is too large to be monitored manually. In this work, a two-stage is proposed with a combination of several features. The first stage is for detecting the predatory conversations while the second step aims to distinguish the predator from the victim in the predatory conversations. The features ensemble used will be combining lexical and behavioral features. The lexical features used include BoW, POS-based, topical, and emotion-based. Meanwhile, the behavioral features used for this work include the number of messages, the average number of words, the number of exclamation marks, the number of questions, sentence complexity and readability, and the number of intentions. SVM was used as a classifier due to its good ability for many text classification tasks. The experiment result shows that BoW with tf - idf term weighting provided the best performance for both PCI and VPD tasks. BoW with tf- idf term weighting obtained an F0.5 score of 0.9893 on PCI and 0.9798 on VPD. The features ensemble can exceed most of the individual features that form it but still cannot beat BoW.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Most prior work has focused on detecting perpetrators' behaviors, leaving a limited understanding of how teens might respond to unwanted advances.
“Yet, most prior work has focused on detecting perpetrators' behaviors, leaving a limited understanding of how teens might respond to such unwanted advances.”
From From Vulnerable to Resilient: Examining Parent and Teen Perceptions on How to Respond to Unwanted Cybergrooming Advances (2026) · cites this paper as [34]
Cites
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278 · see citing works
An Introduction to Information Retrieval
Ceri, S., Bozzon, A., Brambilla, M., Valle, E. D., Fraternali, P., & Quarteroni, S. (2013) · Springer eBooks · doi:10.1007/978-3-642-39314-3_1 · Cited by 854 · see citing works
The impact of preprocessing on text classification
Uysal, A. K., & Günal, S. (2013) · Information Processing & Management · doi:10.1016/j.ipm.2013.08.006 · Cited by 664 · see citing works
Ensemble of feature sets and classification algorithms for sentiment classification
Xia, R., Zong, C., & Li, S. (2011) · Information Sciences · doi:10.1016/j.ins.2010.11.023 · Cited by 583 · see citing works
Empath: Understanding Topic Signals in Large-Scale Text
Fast, E., Chen, B., & Bernstein, M. S. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858535 · Cited by 413 · see citing works
MBT: A Memory-Based Part of Speech Tagger-Generator
Daelemans, W. M. P., Zavrel, J., Berck, P., & Gillis, S. A. (1996) · Research portal (Tilburg University) · doi:10.48550/arxiv.cmp-lg/9607012 · Cited by 305 · see citing works
The prevalence of unwanted online sexual exposure and solicitation among youth: A meta-analysis
Madigan, S., Villani, V., Azzopardi, C., Laut, D., Smith, T., Temple, J. R., Browne, D., & Dimitropoulos, G. (2018) · Journal of Adolescent Health · doi:10.1016/j.jadohealth.2018.03.012 · Cited by 164 · see citing works
Cybering, online grooming and ageplay
Kierkegaard, S. (2007) · Computer Law & Security Report · doi:10.1016/j.clsr.2007.11.004 · Cited by 101 · see citing works
(2012) · PubMed · Cited by 98 · see citing works
Overview of the International Sexual Predator Identification Competition at PAN-2012.
Inches, G., & Crestani, F. (2012) · Cited by 93 · see citing works
Choo, K. R. (2009) · PsycEXTRA Dataset · doi:10.1037/e582922012-001 · Cited by 90 · see citing works
Detecting child grooming behaviour patterns on social media
Cano, A. E., Fernandez, M., & Alani, H. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-13734-6_30 · Cited by 79 · see citing works
Detecting predatory conversations in social media by deep convolutional neural networks
Ebrahimi, M., Suen, C. Y., & Ormandjieva, O. (2016) · Digital Investigation · doi:10.1016/j.diin.2016.07.001 · Cited by 78 · see citing works
Toward spotting the pedophile telling victim from predator in text chats
Pendar, N. (2007) · International Conference on Semantic Computing (ICSC 2007) · doi:10.1109/icsc.2007.32 · Cited by 77 · see citing works
A Two-step Approach for Effective Detection of Misbehaving Users in Chats
Villatoro-Tello, E., Juárez-González, A., Escalante, H. J., Montes-y-Gómez, M., & Villaseñor-Pineda, L. (2012) · Cited by 41 · see citing works
Ensemble Method for Sexual Predators Identification in Online Chats
Fauzi, M. A., & Bours, P. (2020) · 2020 8th International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf49977.2020.9107945 · Cited by 34 · see citing works
Self-citation(2011) · Leicester Research Archive (University of Leicester) · Cited by 33 · see citing works
Utilizing document classification for grooming attack recognition
Michalopoulos, D., & Mavridis, I. K. (2011) · Proceedings - IEEE Symposium on Computers and Communications/IEEE Symposium on Computers and Communications · doi:10.1109/iscc.2011.5983950 · Cited by 28 · see citing works
Detection of child exploiting chats from a mixed chat dataset as a text classification task
Miah, M. W. R., Yearwood, J. L., & Kulkarni, S. (2011) · Cited by 27 · see citing works
A Learning-Based Approach for the Identification of Sexual Predators in Chat Logs.
Parapar, J., Losada, D. E., & Barreiro, Á. (2012) · CLEF (Online Working Notes/Labs/Workshop) · Cited by 27 · see citing works
Sexual predator detection in chats with chained classifiers
Escalante, H. J., Villatoro-Tello, E., Juárez, A. G.-U., Montes-y-Gómez, M., & Villaseñor-Pineda, L. (2013) · Cited by 24 · see citing works
Conversation Level Constraints on Pedophile Detection in Chat Rooms
Peersman, C., Vaassen, F., Asch, V. V., & Daelemans, W. M. P. (2012) · Bristol Research (University of Bristol) · Cited by 23 · see citing works
Identifying Sexual Predators by SVM Classification with Lexical and Behavioral Features.
Morris, C. W., & Hirst, G. (2012) · Cited by 23 · see citing works
Gillam, L., & Vartapetiance, A. (2012) · Surrey Research Insight Open Access (The University of Surrey) · Cited by 20 · see citing works
Predatory Conversation Detection
Borj, P. R., & Bours, P. (2019) · 2019 International Conference on Cyber Security for Emerging Technologies (CSET) · doi:10.1109/cset.2019.8904885 · Cited by 19 · see citing works
Self-citationSexual-predator Detection System based on Social Behavior Biometric (SSB) Features
Wani, M. A., Agarwal, N., & Bours, P. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.05.075 · Cited by 18 · see citing works
Self-citationCombining Predation Heuristics and Chat-Like Features in Sexual Predator Identification.
Hidalgo, J. M. G., & Díaz, A. A. C. (2012) · CLEF (Online Working Notes/Labs/Workshop) · Cited by 14 · see citing works
Information Retrieval and Classification based Approaches for the Sexual Predator Identification.
Ayala, D. V., Castillo, E., Pinto, D., Olmos, I., & León, S. (2012) · CLEF (Online Working Notes/Labs/Workshop) · Cited by 8 · see citing works
Flagged first, then by citations
2 of the 30 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Effectiveness of machine learning methods in detecting grooming: a systematic meta-analytic review
Bianchi, M. L., Castillo, N., Astudillo, C. A., & Ahumada-Méndez, F. (2025) · Scientific Reports · doi:10.1038/s41598-024-83003-4 · Cited by 13 · see citing works
A Survey of Generative AI for Detecting Pedophilia Crimes
Silva, F., Silva, R. R., & Bernardino, J. (2025) · Applied Sciences · doi:10.3390/app15137105 · Cited by 4 · see citing works
Comparing machine learning models with a focus on tone in grooming chat logs
Hamm, L., & McKeever, S. (2025) · Frontiers in Pediatrics · doi:10.3389/fped.2025.1591828 · Cited by 4 · see citing works
Zhang, X., Akter, M., An, H., Liu, M., Zhang, Q., Huang, L., Cho, J.-H., J. Wisniewski, P., & Lee, S. W. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790949
“To combat cybergrooming, prior work has focused on surveillance and detection, using computational techniques such as machine learning (ML), natural language processing (NLP), and data mining to detect perpetrator behavior [32, 34, 59, 72, 76–78].”
SafeCon: AI-Powered Real-Time Cyber Grooming Detection System
Sallahudin, S., Ismail, M., Ali, S., Ahmed, A., & Hameed, M. F. (2025) · VFAST Transactions on Software Engineering · doi:10.21015/vtse.v13i2.2118
- Authors
- Fauzi, M. A., Wolthusen, S., Yang, B., Bours, P., & Yeng, P.
- Affiliations
- Norwegian University of Science and Technology (NO)
- Venue
- 2023 International Conference on Emerging Trends in Networks and Computer Communications (ETNCC)
- Publisher
- IEEE
- Published
- 2023-08-16
- Pages
- 1-6
- OpenAlex
- W4387913690
- Cited by
- 4
- References
- 30
- Citations by year
- 2025: 4
- FWCI
- 0.71
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Emerging Trends in Networks and Computer Communications (ETNCC) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Keywords
- chat conversations, feature ensemble, lexical features, behavioral characteristics, bag-of-words, TF-IDF, support vector machine, text classification, child online safety
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
