Identification & Coding
Classification is merely identification of the data set’s documents and once identified the document is then coded and will be properly stored for later use.
Our Classification module automatically codes all documents in a production for more than 100 document types such as email, memos, court documents, market analysis, corporate finance, agendas, minutes, site reports, lab reports, material safety data sheets, financial projections, SEC docs, and many others.. The module allows end users to find custom document types critical for specific litigation. In addition, the module calculates the email threads, near and far duplicates, and problem documents with no text. Sample data extractions used are: Technical terms from a 60,000+ word Dictionary, Names from a surname directory, several date forms, Email names, and addresses, sent, to, from, cc, email subject and the dates, and site and claim numbers. Kaleidoscope uses a social networking graph (awesome by the way) to display these items. Click here to see it