Semantic Document Clustering for Crime Investigation

Computers are increasingly used as tools to commit crimes such as unauthorized access (hacking), drug trafficking, and child pornography. The proliferation of crimes involving computers has created a demand for special forensic tools that allow investigators to look for evidence on a suspect’s computer by analyzing communications and data on the computer’s storage devices. Motivated by the forensic process at Sûreté du Québec ( SQ ), the Québec provincial police, we propose a new subject-based semantic document clustering model that allows an investigator to cluster documents stored on a suspect’s computer by grouping them into a set of overlapping clusters, each corresponding to a subject of interest initially defined by the investigator.