Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Comparing machine learning models with a focus on tone in grooming chat logs
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Informatics and Media.
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Informatics and Media.ORCID iD: 0000-0002-1970-2884
2025 (English)In: Frontiers in Pediatrics , E-ISSN 2296-2360, Vol. 13, article id 1591828Article in journal (Refereed) Published
Abstract [en]

In online spaces, children are vulnerable to exploitation and sexual predators. Groomers contact minors in online chat rooms with the intent of sexual abuse. This study investigates how new deep learning models compare to traditional machine learning models in detecting grooming conversations and predatory authors. Furthermore, we detect the underlying tones used by predators and explore how these affect detection capabilities. Our goal is to better understand predator tactics and to advance automatic grooming detection in order to protect children in online spaces. The PAN12 chat logs, which contain grooming chat conversations, were used as the dataset for the research. These chat conversations were sorted into sentiments through the DistilBERT classifier based on the predator tone. SVMs and the LLaMA 3.2 1B large language model by Meta were then trained and fine-tuned on the different sentiments. The results measured through precision, recall and F1 score show that the large language model performs better in grooming detection than traditional machine learning. Moreover, performance differences between the positive and negative sentiment are captured and indicate that positive tone improves detection while negative toned grooming conversations have nuanced patterns that are harder to distinguish from non-grooming. This shows that groomers employ varying strategies to gain access to their victims. Lastly, with an F1 score of 0.99 and an F0.5 score of 0.99, the LLaMA 3.2 1B model outperforms both traditional machine learning, as well as previous versions of the large language model in grooming author detection.

Place, publisher, year, edition, pages
Frontiers Media S.A., 2025. Vol. 13, article id 1591828
Keywords [en]
grooming detection, online predators, sentiment analysis, large language models, predator tone, social exchange theory
National Category
Natural Language Processing Other Engineering and Technologies
Identifiers
URN: urn:nbn:se:uu:diva-563634DOI: 10.3389/fped.2025.1591828ISI: 001521788800001PubMedID: 40612489Scopus ID: 2-s2.0-105009924203OAI: oai:DiVA.org:uu-563634DiVA, id: diva2:1984063
Available from: 2025-07-14 Created: 2025-07-14 Last updated: 2025-07-14Bibliographically approved

Open Access in DiVA

fulltext(693 kB)333 downloads
File information
File name FULLTEXT01.pdfFile size 693 kBChecksum SHA-512
3f6b6a63d986449b7d1905c42dc9a045d9dd19b3649e9bae897af38726227ea43610702e4682a610ab0b9659f0c5c9e202e5b747b1a5d8325c0dfe1be378dba8
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMedScopus

Search in DiVA

By author/editor
McKeever, Steve
By organisation
Department of Informatics and Media
In the same journal
Frontiers in Pediatrics
Natural Language ProcessingOther Engineering and Technologies

Search outside of DiVA

GoogleGoogle Scholar
Total: 335 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 447 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf