cascadePy

Global Initiative Against Transnational Organized Crime

cascadePy, developed by the Center for the Analysis of Social Media (CASM) in collaboration with the Global Initiative Against Transnational Organized Crime (GITOC), is a corpus expansion toolkit written in Python. This toolkit specializes in the combination of NLP techniques, information extraction and web harvesting methods, primarily intended for use in open source intelligence (OSINT) against the illicit online wildlife trade. Its primary use is to discover, characterize, and expand the vernacular used by those involved in the illicit wildlife trade, identifying places on the web where this trade is promoted. These tools enable effective collection and detailed analysis of open-source intelligence data.

cascadePy answers the need to combat the illegal online wildlife trade. By integrating advanced natural language processing and information extraction methods, it enables OSINT investigators to discover and analyze communications and advertisements related to illicit activities, thereby improving surveillance and law enforcement strategies.

CascadePy is a Python tool that uses natural language processing, information extraction, and web scraping methods to support open-source intelligence efforts. Its goal is to discover and characterize the language used in the illicit wildlife trade and locate the websites where it is advertised.

CascadePy organizes its analytical logic using pure JSON templates; by operating on the RFC 8259 specification, results can be consumed from browsers, Node.js, or any backend. The cascade model combines declarative objects and maintains the interoperability typical of JSON- and CSV-based exchanges.