A hybrid approach for document analysis in digital forensic domain

Abstract

Our daily life is characterized by the continuous interaction with many devices and technologies, which build a digital ecosystem around each person. In this context, if, for example, it is necessary to investigate the commission of a crime, the adoption of digital forensic sciences is of fundamental importance. These disciplines are in fact concerned with gathering any information that may be of some interest to the legal system, in full respect of its nature and without its characteristics being altered in any way; in this way the probative value of the information collected and its admissibility in the trial are guaranteed. The complexity of the scenario in which the forensic operators are to operate derives from the widespread diffusion of devices with a large variety of characteristics and, mostly, from the heterogeneous and unstructured representation of relevant information. In this work we present a semantic approach for textual document analysis to enrich the correlation process of a forensics investigation