Analytics for Beginners: What Every Attorney Needs to Know

While technology-assisted review (TAR) has become a center of discussion in litigation and a common practice for handling large and daunting cases, less “buzzworthy” analytics tools are often overlooked and underrated—despite the big results they can yield.

Understanding what analytics tools are available and how and when to use them can help you organize and prioritize documents to ultimately save your review team time, and get answers to your clients faster.

If you’re not well acquainted with analytics yet, consider this your introduction—here are four ways it can be your best friend throughout review.

Organization: Setting Up for a Quick Review

When it comes to organizing your data at the onset of review, you can lean on three key text analytics features.

Email threading allows you to tie conversations together and potentially eliminate documents from review. By grouping email conversations, your litigation support team can easily review them in batches.

When assisting its client in responding to a government subpoena, Troutman Sanders eMerge saw the big benefits of email threading, using it to eliminate 148,329 emails with 84,225 attachments. The team was able to focus its efforts on only 66% of emails—those that contained entire conversations or unique attachments.

Near-duplicate detection groups nearly identical documents together. Think about how many different versions of essentially the same documents are saved on your computer. Now imagine if you could, in just a few clicks, bundle all of those similar drafts together. Near-duplicate detection does just that, providing an easy way to view highly similar documents, allowing you to apply designation, issue coding, or privilege decisions to very similar documents quickly and accurately.

Foreign language identification looks at sentence structure to identify the primary language in each document along with any secondary languages. This allows you to more accurately organize documents by language—a pile for French, a pile for German, and so on—and batch them out to foreign language reviewers or translators.

Prioritization: Determine Where You Need to Dig Deeper

Clustering automatically identifies and groups documents with similar concepts, allowing you to organize and prioritize your review much earlier in a case. Clustering labels groups by the most prevalent ideas, and does it without any user input. With clustering, you’ll get a peek at what might be responsive or not responsive, making it easier to batch and rapidly code documents.

One Friday morning, a team at Stradley Ronon Stevens & Young received approximately 7,900 documents related to an insurance matter. Working with a Monday morning deadline, the associate on the case used clustering to help identify all the key documents in the data set and eliminate 94% of the documents as non-responsive.

With categorization, subject matter experts define a category and then feed the system a small group of coded example documents to automatically classify un-reviewed documents for that category. With documents broken down into groups, experts can start reviewing data related to their expertise right away. You can also use categorization to efficiently find important documents from an opposing production.

Investigation: Leave No Stone Unturned

Keyword expansion allows you to get a sense of critical case language and find hidden language, such as project code names or industry jargon. Text analytics finds these words by searching for terms that are conceptually related to your keywords based on the unique language in your data set.

Concept searching analyzes your search query holistically, instead of limiting the search to the exact words or phrases you enter. For example, unlike keyword searching, concept searching will know when you’re looking for information related to Turkey the country, and not turkey the Thanksgiving treat. This type of searching brings back results based on concept, allowing your team to find potentially relevant documents faster. You can even create your “smoking gun” document and then search to see if something similar exists.

Amplification: Boost Your Review Team’s Efforts

Technology-assisted review, as we mentioned, has gotten a lot of attention, as it can help make litigation less costly and tedious. With TAR, your team codes example documents with responsiveness designations, text analytics applies your decisions across the larger data set, and your results are validated with transparent, defensible statistics. You can also use TAR for issue coding. The technology allows your team to accelerate review and amplify efforts across any substantial document set.

When the U.S. Department of Justice investigated the Anheuser Busch InBev merger, McDermott Will & Emery was called upon to review 1.6 million documents that could be relevant to the U.S. DOJ’s requests for information. They had just two months. Within six weeks, McDermott Will & Emery completed productions for the U.S. DOJ and saved over $2 million in review costs using Assisted Review.

Analytics can change the way your team approaches review, no matter how big or small the case—you just need to know when and how to use it. Still have more questions? Feel free to  contact us.

About the Author


Andrea Beckman is a group product manager at kCura for Relativity’s review and analytics features. She has more than 15 years of experience in software development and management, and she holds an MBA from Northwestern University.

Send this to a friend