A Step Towards Detecting Online Grooming -- Identifying Adults Pretending to be Children
Abstract
Online grooming is a major problem in todays society where more and more time is spent online. To become friends and establish a relationship with their young victims in online communities, groomers often pretend to be children. In this paper we describe an approach that can be used to detect if an adult is pretending to be a child in a chat room conversation. The approach involves a two step process wherein authors are first classified as being children or adults, and then each child is being examined and false children distinguished from genuine children. Our results show that even if it is hard to separate ordinary adults from children in chat logs it is possible to distinguish real children from adults pretending to be children with a high accuracy. In this paper we will discuss the accuracy of the methods proposed, as well as the features that were important in their success. We believe that this work is an important step towards automated analysis of chat room conversation to detect and possible attempts of grooming. Our approach where we use text analysis to distinguish adults who are pretending to be children from actual children could be used to inform children about the true age of the person that they are communicating. This would be a step towards making the Internet more secure for young children and eliminate grooming.
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?
Ashcroft et al. [58] used the Perverted-Justice website to include texts written by predators and also used book reviews, blogs, and chat logs for non-predatory texts.
“Ashcroft et al. [58] used the Perverted-Justice website to include texts written by predators and also used book reviews, blogs, and chat logs for non-predatory texts.”
From Online grooming detection: A comprehensive survey of child exploitation in chat logs (2023) · cites this paper as [58]
It is possible to distinguish a child from an adult, although it could be more challenging in short text messages compared to books and reviews.
“Ashcroft et al. [58] showed that it is possible to distinguish a child from an adult, although it could be more challenging in short text messages compared to books and reviews.”
From Online grooming detection: A comprehensive survey of child exploitation in chat logs (2023) · cites this paper as [58]
Most computer science literature focuses on detecting perpetrators' behaviors using machine learning and natural language processing techniques.
“To combat cybergrooming, researchers have developed numerous computational approaches, with most computer science literature focuses on detecting perpetrators' behaviors using machine learning (ML) and natural language processing (NLP) techniques (e.g., [5, 16-19, 3234, 42, 44, 48, 59, 62, 72, 76-78]).”
From From Vulnerable to Resilient: Examining Parent and Teen Perceptions on How to Respond to Unwanted Cybergrooming Advances (2026) · cites this paper as [16]
The anonymity of the internet allows individuals to create fake profiles as peers or trustworthy figures, making it challenging for children to discern malicious intent.
“The anonymity of the internet allows these individuals to create fake profiles as peers or trustworthy figures, making it challenging for children to discern malicious intent (Ashcroft et al., 2015).”
From Virtual Reality Risks for Children in the Metaverse: An Examination through Criminological Perspectives (2026) · cites this paper as Ashcroft et al., 2015
Cites
Experiments with a new boosting algorithm
Freund, Y., & Schapire, R. E. (1996) · Cited by 8,189 · see citing works
Hidden factors and hidden topics
McAuley, J., & Leskovec, J. (2013) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/2507157.2507163 · Cited by 1,565 · see citing works
A survey of modern authorship attribution methods
Stamatatos, E. (2009) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.21001 · Cited by 1,176 · see citing works
Juola, P. (2007) · now publishers, Inc. eBooks · doi:10.1561/9781601981196 · Cited by 623 · see citing works
Effects of Age and Gender on Blogging
Schler, J., Koppel, M., Argamon, S., & Pennebaker, J. W. (2005) · National Conference on Artificial Intelligence · Cited by 590 · see citing works
Zheng, R., Li, J., Chen, H., & Huang, Z. (2006) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.20316 · Cited by 519 · cited 2× · see citing works
“Much less research has been devoted to problems with a large number of potential authors and smaller quantities of text material, or to the cyberspace domain in general [1].”
BackgroundMethodJuola, P. (2008) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000005 · Cited by 505 · see citing works
Abbasi, A., & Chen, H. (2008) · ACM Transactions on Information Systems · doi:10.1145/1344411.1344413 · Cited by 405 · see citing works
Automatically profiling the author of an anonymous text
Argamon, S., Koppel, M., Pennebaker, J. W., & Schler, J. (2009) · Communications of the ACM · doi:10.1145/1461928.1461959 · Cited by 376 · see citing works
On the Feasibility of Internet-Scale Author Identification
Narayanan, A., Paskov, H., Gong, N. Z., Bethencourt, J., Stefanov, E., Shin, E. C. R., & Song, D. (2012) · 2012 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2012.46 · Cited by 261 · see citing works
Predicting age and gender in online social networks
Peersman, C., Daelemans, W., & Van Vaerenbergh, L. (2011) · Proceedings of the 3rd international workshop on Search and mining user-generated contents · doi:10.1145/2065023.2065035 · Cited by 260 · see citing works
Overview of the 2nd Author Profiling Task at PAN 2014
Rangel, F., Rosso, P., Koppel, M., Stamatatos, E., & Inches, G. (2013) · RiuNet (Universitat Politècnica de València) · Cited by 201 · see citing works
Stylometric analysis of bloggers’ age and gender
Goswami, S., Sarkar, S., & Rustagi, M. (2009) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v3i1.13992 · Cited by 140 · see citing works
Detecting multiple aliases in social media
Johansson, F., Kaati, L., & Shrestha, A. (2013) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1145/2492517.2500261 · Cited by 55 · see citing works
Self-citationCharacterizing Pedophile Conversations on the Internet using Online Grooming
Gupta, A., Kumaraguru, P., & Sureka, A. (2012) · arXiv · doi:10.48550/arxiv.1208.4324 · Cited by 45 · 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
Negobot: A Conversational Agent Based on Game Theory for the Detection of Paedophile Behaviour
Laorden, C., Galán-García, P., Santos, I., Sanz, B., Hidalgo, J. M. G., & Bringas, P. G. (2012) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-33018-6_27 · 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
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
Tam, J., & Martell, C. H. (2009) · 2009 IEEE International Conference on Semantic Computing · doi:10.1109/icsc.2009.37 · Cited by 21 · see citing works
De‐Arteaga, M., Jiménez, S., Dueñas, G., Mancera, S., & Baquero, J. (2013) · Cited by 11 · see citing works
Flagged first, then by citations
3 of the 25 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Razi, A., Kim, S., Alsoubai, A., Stringhini, G., Solorio, T., De Choudhury, M., & Wisniewski, P. J. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3479609 · Cited by 95 · see citing works
Razi, A., Alsoubai, A., Kim, S., Ali, S., Stringhini, G., De Choudhury, M., & Wisniewski, P. J. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579522 · Cited by 52 · see citing works
Early detection of deception and aggressiveness using profile-based representations
Escalante, H. J., Villatoro-Tello, E., Garza, S. E., López-Monroy, A. P., Montes-y-Gómez, M., & Villaseñor-Pineda, L. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.07.040 · Cited by 44 · see citing works
Online grooming detection: A comprehensive survey of child exploitation in chat logs
Borj, P. R., Raja, K., & Bours, P. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110039 · Cited by 38 · see citing works
Detection and prevention measures for cyberbullying and online grooming
Upadhyay, A., Chaudhari, A., Arunesh, Ghale, S., & Pawar, S. S. (2017) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc.2017.8068605 · Cited by 11 · see citing works
Revolution of AI-Enabled Health Care Chat-Bot System for Patient Assistance
Sagar, R. H., Ashraf, T., Sharma, A., Goud, K. S. R., Sahana, S., & Sagar, A. K. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-3067-5_18 · Cited by 11 · see citing works
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
Classification of online grooming on chat logs using two term weighting schemes
Sulaiman, N. R., & Md. Siraj, M. (2019) · International Journal of Innovative Computing · doi:10.11113/ijic.v9n2.239 · Cited by 5 · see citing works
Effective, Explainable and Ethical: AI for Law Enforcement and Community Safety
Wilson, C., Dalins, J., & Rolan, G. (2020) · IEEE/ITU International Conference on Artificial Intelligence for Good (AI4G) · doi:10.1109/ai4g50087.2020.9311021 · Cited by 4 · see citing works
Prevention of Emotional Entrapment of Children on Social Media
Kirupalini, S., Baskar, A., Ramesh, A., Rengarajan, G., Gowri, S., Swetha, S., & Sangeetha, D. (2021) · International Conference on Emerging Techniques in Computational Intelligence (ICETCI) · doi:10.1109/icetci51973.2021.9574068 · Cited by 4 · see citing works
MALIGNANT SKIN CANCER DETECTION USING CONVOLUTIONAL NEURAL NETWORKING
Sagar, R. H., Bingi, A., Pola, A., Goud, K. S. R., Ashraf, T., & Sahana, S. (2021) · International Journal of Technical Research & Science · doi:10.30780/ijtrs.v06.i05.001 · Cited by 3 · see citing works
Martellozzo, E., Bradbury, P., Farr, R., & Davidson, J. (2026) · Cambridge University Press eBooks · doi:10.1017/9781009620161 · Cited by 2 · see citing works
Early Recognition of the Speaker’s Age
Kupcová, E., Haluška, R., Popovič, M., Pleva, M., Heng, M. S., & Bours, P. (2023) · International Conference on Emerging eLearning Technologies and Applications (ICETA) · doi:10.1109/iceta61311.2023.10343924 · Cited by 2 · see citing works
Jaccheri, L., Mishra, D., Houmb, S. H., Omerovic, A., & Papavlasopoulou, S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-66715-7_16 · Cited by 2 · see citing works
A child recognition system based on image selection patterns
Nezhad, M. M., & Mehrnezhad, M. (2018) · Workshop on Socio-Technical Aspects in Security and Trust (STAST) · doi:10.1145/3167996.3168003 · Cited by 1 · 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
“…cyber-grooming, researchers have developed numerous computational approaches, with most computer science literature focuses on detecting perpetrators’ behaviors using machine learning (ML) and natural language processing (NLP) techniques (e.g., [5, 16–19, 32– 34, 42, 44, 48, 59, 62, 72, 76–78]).”
Ensure Safe Internet for Children and Teenagers Using Deep Learning
Nazira, F. A., Gosh, S., Nur, K. M., Singh, S. P., & Mridha, M. F. (2022) · International Conference on Decision Aid Sciences and Applications (DASA) · doi:10.1109/dasa54658.2022.9765035
‘Catfishes: How do they reel us in?’ Exploring adolescent vulnerabilities to online grooming
Boland, L., & Worthington, R. (2023) · Forensic Update · doi:10.53841/bpsfu.2023.1.143.12
A Social Media System for detecting Child Predators
Kasar, V., Patil, D. H., Fernandes, S., Chillarge, A., & Abuj, V. (2023) · International Conference on Advanced Computing Technologies and Applications (ICACTA) · doi:10.1109/icacta58201.2023.10392579
- Authors
- Ashcroft, M., Kaati, L., & Meyer, M.
- Affiliations
- Uppsala University (SE)
- Venue
- 2015 European Intelligence and Security Informatics Conference
- Publisher
- IEEE
- Published
- 2015-09
- Pages
- 98-104
- OpenAlex
- W2245533313
- Cited by
- 18
- References
- 25
- Citations by year
- 2026: 1 · 2025: 1 · 2023: 4 · 2022: 2 · 2021: 4 · 2020: 1 · 2019: 1 · 2018: 1 · 2017: 3
- FWCI
- 0.75
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- European Intelligence and Security Informatics Conference (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Keywords
- online grooming, text classification
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
