The authors report state-of-the-art detection of drug, weapon, and credential sales across dark web and social platforms using a semi-supervised ensemble over fine-tuned ModernBERT embeddings plus manual document features (F1 0.935).
Information needs of drug users on a local dark web marketplace,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Language Model-Driven Semi-Supervised Ensemble Framework for Illicit Market Detection Across Deep/Dark Web and Social Platforms
The authors report state-of-the-art detection of drug, weapon, and credential sales across dark web and social platforms using a semi-supervised ensemble over fine-tuned ModernBERT embeddings plus manual document features (F1 0.935).