CFL has developed a suite of programs under the broad head of CopyCatch, all designed to find similarities between documents using whole documents, sentences or phrases rather than the more generally used keyword queries. There are versions which cover individual through to corporation-wide use.

The programs are Computational because they require electronic documents to work with and apply our own sophisticated algorithms to detect similarity. They are Forensic because they are designed to provide evidential data for use in disciplinary hearings and courts, although this is not their only use, of course. And they are Linguistic because the algorithms are primarily based on the observed use of language rather than on statistical or mathematical modelling, and work in most languages.

All the programs can compare sets of documents with each other or with larger stores of related material. They can all find similarity below the sentence level and are all designed to be able to identify such similarity even with changes in word order, insertions or deletions.

Copycatch Gold has been used by individual university teachers for a number of years to monitor student work for plagiarism or collusion.

Copycatch Investigator is actually a set of algorithms designed for large-scale users, and is normally tailored for specific purposes, from visual interfaces to automated monitoring systems running on very powerful multi-threading computers.

The other tools listed are used by Forensic Linguists to gather and assess evidence in cases of malicious emails, threatening letters and other suspect written material. CFL uses them in consultancy work, but they are also used by university researchers and law enforcement investigators.

• Powerful plagiarism and collusion detection
• Sophisticated searching
• Fast, scalable, multi-platform software written in Java