ABSTRACT
In this chapter the process of building the source corpus will be presented. A first part will be dedicated ransomware case studies focusing on the four major ransomware and early attempts. Subsequently the Chapter presents a preliminary introduction on documentation representativeness and the importance of relying on authoritative types of documentation to start the information retrieval process on a specific subject, in this case the association of ransomware with the vulnerabilities in order to provide a means through which a prediction of future cyber attacks can be possible to achieve. The second part will cover the specificity of the corpus compiled for the purposes of this research activity expanding on the features characterizing the documentation under analysis and the granularity of information contained in it meant to be studied for the extraction of the main concepts related to the knowledge framework of ransomware.
