Analytics tools for eDiscovery are powerful, proven and readily available. They serve a number of critical strategic purposes. These include improved review efficiency, minimizing human review to cut costs and more effective review for substantive issues in the case.
Despite their proven value, eDiscovery analytics tools remain widely underutilized. One of the biggest barriers to greater adoption of analytics is a misplaced emphasis on what instead of why. Too often the discussion focuses on how the tools work instead of how they help.
Part one of this article offers two strategic reasons – and a bonus reason – why you should use eDiscovery analytics. Part two will discuss two more reasons to use analytics. The use case examples are meant to be illustrative only. Most analytics tools can be deployed to serve a variety of ends.
Reason #1: Improve review efficiency
The first reason to use analytics is to improve review efficiency. More efficient review means less lawyer time spent reading documents. Less lawyer time results in lower cost of review. Other significant benefits are improved deadline responsiveness and freeing up resources for other tasks.
Analytics tools are excellent at identifying similarities and relationships within a set of documents. Related documents can then be grouped together so a single reviewer sees all the documents in a group. This is a highly efficient approach to review.
Related documents can be quickly reviewed and batch-coded for responsiveness, privilege and issues. Batching related documents also eliminates coding inconsistencies. Inconsistent coding judgments are inevitable when related documents are dispersed among multiple reviewers.
Email thread analysis is the most widely used analytics tool for grouping related documents. It analyzes the entire dataset to locate all emails in a string (original email, replies, forwards, replies to forwards, etc.). The email string is displayed in an easy-to-read format resembling an email inbox. The most advanced email thread analysis tools even identify “missing” emails, which may indicate a gap in the collection or possible spoliation.
Near-duplicate analysis is another powerful and easy-to-use tool for grouping related documents. Near-dupe identifies multiple versions and drafts of a document. The group is sorted by degree of similarity, from most to least similar. Differences between documents are redlined for easy comparison.
Reason #2: Cull non-responsive documents prior to review
The most effective way to lower review costs is to not review large numbers of documents. Analytics makes this possible by using technology to identify non-responsive documents. With appropriate quality control, analytics eliminates the need for lawyer review of some (often significant) portion of the dataset. This is a potentially huge cost-savings opportunity.
Concept analysis is one of the best options for identifying non-responsive documents. An example is the clustering tool in Relativity. Relativity clustering uses the index that was built during processing to identify similar ideas or concepts within the dataset. (My article eDiscovery Processing Basics for Lawyers explains indexing.) It then identifies and groups documents according to concept.
A lawyer or other knowledgeable member of the case team assesses the potential relevance of the concepts. If the lawyer determines that the concept isn’t relevant to the issues in the case, all of the documents within that concept group can be batch-coded as non-responsive without being reviewed.
Clustering commonly identifies numerous obviously non-relevant concepts. These may range anywhere from an unrelated product to a custodian’s summer vacation. Of course, clustering is also good for identifying relevant documents. The main limitation of concept analysis tools is that they aren’t effective for non-text files like spreadsheets and multimedia
Bonus reason: Single purpose tools
The tools described so far can be deployed to achieve multiple strategic goals. However, some analytics tools serve only a single purpose. An example is foreign language identification. As the name indicates, it analyzes the dataset to locate non-English language text and identify the foreign language(s). Although necessarily limited in their application, single-purpose tools are incredibly helpful in the right circumstances.
There are many good reasons to use eDiscovery analytics. Part two of this article will discuss two more ways you can use analytics to improve the quality of review while simultaneously lowering overall eDiscovery cost.
Helen Geib is General Counsel and Practice Support Consultant for QDiscovery. Prior to joining QDiscovery, Helen practiced law in the intellectual property litigation department of Barnes and Thornburg’s Indianapolis office where her responsibilities included managing large scale discovery and motion practice. She brings that experience and perspective to her work as an eDiscovery consultant. She also provides trial consulting services in civil and criminal cases. Helen has published articles on topics in eDiscovery and trial technology. She is a member of the bar of the State of Indiana and the US District Court for the Southern District of Indiana and a registered patent attorney.
This post is for general informational and educational purposes only. It is not intended as legal advice or to substitute for legal counsel, and does not create an attorney-client privilege.