The tools in the analysis suite are typically used by Forensic Linguists in law enforcement to gather and assess evidence in cases of malicious emails, threatening letters and other suspect written material.
Lexical Feature Marker (LFM)
LFM deconstructs language into its functional and grammatical components. While inherently capable of identifying "true" language it can additionally be augmented to recognise slang and business or technical terminology. Used for instruction as well as investigation.
An automatic summarisation system which uses an approach designed to produce summaries of a length and content which can be varied by the user.
CopyCatch Analyst offers detailed numerical, statistical, phrasal and vocabulary analysis of texts for authorship identification, witness and suspect statement analysis and stylometry.
CiteReader recognises properly referenced citations in documents without referencing external data. By extension, unacknowledged material can be recognised and flagged to a user, and the highlighted material used to look for potential sources.
Jangle (JAccard N-Gram Lexical Evaluator)
Developed initially to compare and evaluate large quantities of emails, Jangle provides a way of assessing the similarity of one author to any of the other authors in a given set using samples of word n-grams and the Jaccard similarity coefficient. Tests the hypothesis that authors will look more like themselves than other authors, even when writing on the same subject.