Changes in the US Federal Rules of Civil Procedure in 2006 made electronic documents part of the evidence material for a case.1 This led to an “e-discovery revolution,” and natural language processing (NLP) technologies became standard tools in the document review process in civil litigation.2 This was welcome news for investigators and litigators, since nowadays the most interesting and substantial pieces of evidence are often contained in electronic documents, particularly email conversations. However, these legal changes coincided with the explosion of available data, and the sheer volume of electronic information has made it necessary to search for new ways to handle and review electronic information.3