Classifying illicit dark web content through zero-shot prompting: An empirical study with GPT models

This study evaluates the classification performance of four GPT-based models (GPT-4.1, GPT-4.1-mini, GPT-4.1-nano, and o4-mini) under zero-shot prompting conditions on the complete, multilingual CoDA dataset of Dark Web content, comprising 10 illicit activity categories. The models GPT-4.1, GPT-4.1-...

Descripción completa

Detalles Bibliográficos
Autores: Domínguez Díaz, Adrián|||0000-0001-7632-8609, Marcos Ortega, Luis de|||0000-0003-0718-8774, Prado Sánchez, Víctor Pablo|||0009-0008-0392-255X, Rodríguez García, Daniel|||0000-0002-2887-0185, Martínez Herraiz, José Javier|||0000-0002-2351-7163
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/67901
Acceso en línea:http://hdl.handle.net/10017/67901
https://dx.doi.org/10.1016/j.ipm.2025.104476
Access Level:acceso abierto
Palabra clave:Zero-shot
GPT
Text classification
Illicit activities
Informática
Computer science
Descripción
Sumario:This study evaluates the classification performance of four GPT-based models (GPT-4.1, GPT-4.1-mini, GPT-4.1-nano, and o4-mini) under zero-shot prompting conditions on the complete, multilingual CoDA dataset of Dark Web content, comprising 10 illicit activity categories. The models GPT-4.1, GPT-4.1-mini, and o4-mini achieve a weighted F1 score of 0.885, surpassing prior zero-shot baselines on this dataset. Stability analysis using TARa@10 demonstrates high output consistency for GPT-4.1 (0.964) and GPT-4.1-mini (0.970), indicating their reliability for operational use. Multilingual evaluation reveals only a modest English vs. non-English performance gap for GPT-4.1 (0.031), while other models perform comparably across languages. The strongest results appear in Drugs, Gambling, and Porn (F1 > 0.9), whereas lower scores are observed in ambiguous or overlapping categories like Violence (F1 <= 0.76) or Crypto (F1 <= 0.84). A qualitative review of misclassifications suggests that some model predictions align with reasonable semantic interpretations, potentially highlighting annotation inconsistencies. This work establishes a performance baseline for GPT-based models in zero-shot classification of multilingual Dark Web content and underscores the importance of clear category definitions for effective deployment.