1. ANITA's text analysis services for fighting online illegal trafficking of drugs, weapons and false charity claims: A lateral thinking approach
- Author
-
Masucci Vincenzo, Colombo Jacopo, Caterino Ciro, and Nardelli Filippo
- Subjects
illegal trafficking ,drugs ,weapons ,natural language processing (nlp) ,natural language understanding (nlu) ,black market ,artificial intelligence (ai) ,Social pathology. Social and public welfare. Criminology ,HV1-9960 - Abstract
ANITA platform aims at improving investigation capabilities of law enforcement agencies (LEAs) by delivering a set of tools and techniques to efficiently address online illegal trafficking of counterfeit/falsified medicines, novel psychoactive substances (NPS), drugs, and weapons with Artificial Intelligence (AI). Expert.ai has developed a dedicated written content analysis engine to support investigative activity. The market already offers several solutions adopting AI and in particular Machine Learning (ML) to support investigative activities. The particularity of the work carried out in the ANITA project is to adopt a lateral thinking approach and the supervised generation of knowledge from the analysed contents. Rather than focusing on searching for specific proper names of substances, weapons, NPS, etc. that are constantly evolving in considerable speed, we propose to concentrate on searching for precursors, namely collateral concepts related with the target of the investigation. Is the case of accessories for weapons such as sights for rifles or glass vessels used to produce the drugs themselves? This approach is not compatible with the use of ML, but the use of deep semantic analysis of the text is necessary. This article reports the system's ability to automatically identify precursors and generate stimuli and knowledge which the investigator must validate; that enhances the creative and intuitive approach (serendipity) to investigation combining the best of the detective's skills with the power of AI and in particular Natural Language Understanding (NLU).
- Published
- 2021
- Full Text
- View/download PDF