ARCHIVED CONTENT
You are viewing ARCHIVED CONTENT released online between 1 April 2010 and 24 August 2018 or content that has been selectively archived and is no longer active. Content in this archive is NOT UPDATED, and links may not function.By Herbert L. Roitblat
One advantage of using computer assisted review, for example, predictive coding, is that the computer does, in fact, examine all of the available evidence in a document. Unlike human reviewers, the computer sees all parts of the elephant and, as a result, consistently judges documents based on the full complement of information in them. Each of reviewer judgment used to train the system may be based on a sample of features, but the computer system aggregates all of these partial judgments and chooses the category that is most consistent with this aggregation of cues, rather than with any individual sample. As a result, the computer can be more consistent than the human reviewer who trains trains it. Under appropriate circumstances, this consistency further enhances the accuracy and reliability of computer assisted review.