Early Detection of Cyber Grooming in Online Conversations: A Dynamic Trust Model and Sliding Window Approach
Abstract
Detecting predatory behavior in online conversations is crucial for ensuring the safety of its users, in particular minors. This study investigates the performance of various machine learning models in identifying predatory conversations using a sliding window approach, that looks at a set number of messages in an online conversation. The models are evaluated based on their accuracy, precision, recall, and F1scores. The results showed that certain models performed differently with different window sizes. The study has some limitations, such as small dataset sizes and fixed sliding window sizes. This warrants further investigation, and future research should focus on evaluating the models on a bigger dataset, exploring other window sizes, and considering different hyper-parameters for the evaluation of the risk-scoring.
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 [32]
Cites
Estimation of the Youden Index and its Associated Cutoff Point
Fluss, R., Faraggi, D., & Reiser, B. (2005) · Biometrical Journal · doi:10.1002/bimj.200410135 · Cited by 2,604 · see citing works
Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation
Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006) · Lecture Notes in Computer Science · doi:10.1007/11941439_114 · Cited by 1,974 · see citing works
(2012) · PubMed · Cited by 98 · 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
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-citationDetection of Cyber Grooming in Online Conversation
Bours, P., & Kulsrud, H. (2019) · 2019 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs47025.2019.9035090 · Cited by 27 · see citing works
Self-citationEarly Detection of Sexual Predators in Chats
Vogt, M., Leser, U., & Akbik, A. (2021) · doi:10.18653/v1/2021.acl-long.386 · Cited by 18 · see citing works
Continuous User Authentication and Identification: Combination of Security & Forensics
Mondal, S. (2016) · Cited by 2 · see citing works
Flagged first, then by citations
2 of the 11 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
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].”
Half the Story - Early Cyber Grooming Detection Using Messages from One Participant
Bours, P., Jenssen, S., & Waasjø, S. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29723-5_23
Self-citation
- Authors
- Eilifsen, T. N., Shrestha, B., & Bours, P.
- Affiliations
- Norwegian University of Science and Technology (NO)
- Venue
- 2023 21st International Conference on Emerging eLearning Technologies and Applications (ICETA)
- Publisher
- IEEE
- Published
- 2023-10-26
- Pages
- 129-134
- OpenAlex
- W4389610665
- Cited by
- 3
- References
- 11
- Citations by year
- 2026: 1 · 2025: 2
- FWCI
- 0.53
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Emerging eLearning Technologies and Applications (ICETA) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Keywords
- online grooming, online discourse, dynamic trust model, sliding window, window size, risk scoring, child online safety, classifier comparison
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
