Content Analyst: a Latent Semantic Indexing tool for Issue Coding, Concept Categorization and Searching of Litigation documents

By: Joe Thorpe

Content Analyst: performs categorization (for issue coding) and searching by concept. This is a purely mathematical approach which pays close attention to words and "phrase concept" co-occurrence over a large body of documents. If in your documents for example there are a number of references made to my property management group called the Endurance Management Group (EMG) and one of the properties that they manage for me is called the Thorpe Towers, the software will figure that out. A search for Endurance Management Group will return documents with the Thorpe property even if no reference is made to EMG or Endurance. And, if that document involves discussion of a complicated 1031 exchange, you can use that document to train a category for 1031 and it will get each reference where found in other documents -- even when the transaction is discussed in other ways not specifically referencing the term 1031. Here is a link that speaks generically of the LSI approach which does a much better job of describing how (and why) it works.
http://knowledgesearch.org/lsi/lsa_definition.htm

There is a competing technology to the LSI approach stemming from the "Bayesian" set of algorithms -- the objective of categorization software using the Bayesian approach is to create a taxonomy and structure thusly.
This is a linguistics based approach, the idea behind which is to index the entire corpus of data and let the program generate the common topics that it finds and organize the documents against these topics. This approach tends to work better when the documents are all articles each following a well organized theme.
In business communications (i.e. e-mail, etc.) conversations are typically all over the map. Too often the subject line bears no resemblance to the key points in an e-mail thread nor does the writer put much organization into the content. For documents in litigation databases, we found very little value in the Bayesian methodology.

Our preference for the Content Analyst engine using the LSI method culminated a four year search for a categorization tool that really provided value to the mining and organization for an unstructured document database as is the case with a large collection of litigation documents. This product would not be as useful in a Concordance or a Summation environment – it’s not yet integrated so it wouldn’t be interactive through a document review process - but it is supported in any of the following three hosted review platforms: Relativity (by kCura), iConect and Eclipse by IPRO. Each has integration to the Content Analyst system. All are very well respected litigation database platforms (for online document review) and each provides the flexibility of being able to re analyze and index throughout the document review process.

International Litigation Services, Inc.

jthorpe@ils-ipp.com

eDiscovery a.k.a. “The Money Pit”

By Joe Thorpe & Diane Barry Esq.

Are Rising Discovery Costs Inevitable?

Most corporations long ago resigned themselves to the fact that litigation is just another part of the cost of doing business. Fortunately, given the current state of the economy, many corporations are re-examining this “fact.” Across the corporation, departmental budgets are being reconsidered and trimmed of excess. One of the most intransigent items is the litigation budget. Costs are rising sharply, and corporations are often frustrated in their efforts to contain costs which seem largely beyond their control.

Discovery costs are often the highest price items in the litigation equation, and discovery costs associated with ESI lead the pack. The sheer volume of ESI (electronically stored information) which a corporation creates during the ordinary course of its business is an endlessly increasing number. In turn, this number has pushed discovery costs into a dizzying inflationary spiral. Identification, collection, production and review costs can be staggering, raising the price tag of even relatively small litigation matters.

Many corporations turned to their counsel and eDiscovery experts to assist them in taming the wild costs associated with discovery. Their advice: be prepared. Litigation Preparedness programs were designed and implemented to solve the rising costs of untamed ESI discovery. The expert advice: if the corporation only had a better understanding of its information and regulatory and legal requirements, and used “best practices” for collection, preservation and production, costs would be reduced. Improvements were made, but usually, litigation costs did not reverse. Instead, they simply rose at a slower rate. Substantial savings have been made through preparedness but no essential change in the inexorable rise of litigation costs has been achieved.

The Process Is Broken

For corporations which have embraced litigation preparedness, litigation risks have been made more manageable. There have also been substantial reductions in the per item costs to collect, review and produce discovery materials. However, since the number of paper and data files which need to be produced in litigation continue to rise almost exponentially, overall discovery costs likewise continue to rise sharply.

This is because despite improvements to the current discovery and production process, the process itself remains the same. Most companies continue the age old practice of coordinating with outside counsel to work the discovery process. It is time to consider not the individual work points on this process, but the inevitability of the process itself. The process does not lend itself to cost reductions because the process itself is broken.

Studies show that where eDiscovery is involved, up to $.70 of the litigation dollar is spent on the identification, collection, processing, review and production of ESI. This statement is misleading, in that it gives the impression that all points on the listed work spectrum have an equal share of the associated costs. (i.e., that collection has the same proportion of the overall cost as production). Any corporation which has examined its legal bills has come to the conclusion that this is not true. The single most expensive point of this process (more than 80% of the discovery costs) is and will continue to be legal review. The costs of identification, preservation and collection pale in comparison. Attempts to reduce the overall costs of discovery by containing the costs associated with these points have failed to produce the desired level of savings.

For discussion, let’s look at the below figures, which illustrate the costs associated with a basic ESI production.

The below chart assume that there are 75,000 page equivalents, or 15,000 documents per gigabyte (roughly 5 pages per document).

Matter #1

Service	Volume (GB)	Doc Count	Cost
Data Collection	20	300,000	$1000
Process and Filter	20	300,000	$12,000
Filter Data	14	210,000
Attorney Review	14	210,000	$420,000
Hosting	14		$6,300
Production		136,500	$68,250
Total			$507,550

The costing assumptions are as follows:

Data Collection	$50 per GB
Process and Filter	$600 per GB
Volumes Remaining (GB) after Filtering	14 GB
Three months hosting charges (14 GB)	$150 per GB per mo.
Attorney Review	$150 per hour
Docs reviewed per day per attorney	600
Production	$.10 per page

As you can see, the collection, processing, filtering, hosting and production charges, taken all together, represent less than 20% of the total cost. The document review costs are what push this project into orbit.

Most corporations are approaching the process through costs containment, and as a result, are achieving only limited success. They have discussed the costs with their outside firms asking them to come up with a different plan for document review. Some have instructed them to explore the use of contract attorneys (which could easily halve the document review costs.) Still others have explored using offshore document reviewers, which has the potential to lower costs even further. All of these options cut costs, but the overall costs of discovery continue to rise.

When the Corporation Controls the Process

The time has come to admit that this process is broken. Reducing the price points of this process will never provide corporations with the cost reductions they seek. Corporations must adopt a different model if discovery costs are ever to be brought under control. Most specifically, corporations must place themselves firmly in the driver’s seat and change institutional practices which abdicate responsibility for basic discovery decisions in favor of outside counsel.

Let us say up front, this article is not intended to bash or otherwise cast full blame on outside counsel. Instead, it is our intention to point out that outside counsel and their corporation clients have different goals and perspectives on the discovery process. Many of outside counsel’s discovery process decisions are rational and necessary from their point of view, but fail to address the considerations, including the cost considerations, dear to corporations.

Problems arose for most corporations years ago when it became standard practice to outsource ESI discovery management to outside law firms. A decade ago, ESI discovery took many corporations by surprise. A timely response required a fair amount of technical expertise and practical know how, and corporate IT resources were otherwise occupied with the day to day business of the business. Rather than build in-house expertise and resources, corporations elected to outsource. As this was a litigation related issue, it was reasonable to outsource it to litigation counsel.

This decision has proved a costly one. First, few outside counsel firms have as much expertise in the technical aspects of ESI discovery as they have with the legal and strategic aspects of a litigation matter. And yet, they are responsible for designing and managing the technical aspects of the corporation’s ESI discovery. Also, many corporations engage multiple outside counsel firms. As a result, a corporation can have as many different processes for producing ESI as it has outside counsel. Finally, an outside law firm lacks the global view of the corporation’s documents and total litigation matters which inside counsel must have. Outsourcing ESI discovery to outside counsel guarantees that each matter’s discovery will be considered in isolation, with work common to more than one litigation being performed (and paid for) again and again (and again.)

The answer is for corporations to drastically redesign their model for management of ESI discovery. Rather than outsourcing discovery decisions to law firms, corporations must take up the management role.

Consider the following example. Many corporations are serial litigants, and certain documents are in constant demand. The email of the head of sales for a particular year may be of interest in several ongoing and future litigation matters. Under the outsourcing model, that executive’s laptop and emails will be sent to multiple sets of outside counsel for privilege and relevance review. The corporation will therefore pay for privilege review costs as many times as there are litigation matters which request those files. The outside law firms can hardly be blamed. They have no information to let them know which files have been reviewed already, and what decisions were made as to each record. They are not provided with the TIFF image or PDF of the document created in a prior litigation. No one tells them that the document was produced to the SEC last year (privileged or not). Therefore, each outside law firm receives documents for a matter, it starts from scratch: identify, collect, process, review, produce. The costs for multiple treatments of the same documents are paid for by the corporation multiple times each year.

Consider also the costs associated with responding to federal court 26(f) conference preparation requirements. The law firm requests the documents it wants, and requests the formats most convenient for its systems. These choices are not always the most cost effective or convenient for the corporation. (The corporation usually finds out after the agreements have been made.)

Do your corporation personnel like to use MACs? Most litigation systems don’t handle MAC files well. A law firm may have only one client with this need (your corporation). Your matters always need it. A serial user will always get a better price than a single matter license. The same goes for foreign language translation, cross-lingual search tools (search in English and get results in Japanese); and foreign language search tools.

Rewind and consider the same litigation matters and how they would have proceeded if the corporation were in charge of the discovery issues. First, the corporation is in the best position to store and track the complete and uniform treatment of its own litigation discovery materials. The corporation could keep a litigation ready archive, storing litigation ready copies of the documents (metadata intact and images where they are available). Any prior decisions regarding each document can be stored in the same database record. This document was claimed as privileged – in X v. Y litigation, on date Z. When a litigation matter commenced, the store could be searched, and relevant materials exported out. A complete history of the document could go with it, including its prior review treatment. (This item is privileged, and was reviewed in 2007 by law firm X). For most purposes, if the item was reviewed before, it need not be reviewed again – proceed directly to production or to privilege log. Skip attorney review for this item.

The corporation could own the hosting and review platforms – either hosting the data through in-house resources, or by contracting directly with outsource companies. When the corporation owns the keys to the system, it can let in which ever counsel it deems appropriate. If it changes law firms, passwords/keys to the system can be almost instantaneously withdrawn and new keys to the system provided to the new outside counsel. There is no need to negotiate the return of litigation documents and records. The corporation never gave up control and therefore still has them all.

Looking at the process this way, let’s look again at our ESI review model.

In this model, the corporation has assumed responsibility for building an eDiscovery process, and retains control while working with an outside law firm. Multi processing and review costs are avoided; uniform results maintained; individual corporate needs (MAC and foreign language issues) are met; litigation duties are fulfilled.

Matter #2

In this example we assumed a rate of 40% recurrence (10 custodians, four of which were previously collected in matter #1). Therefore, only 60% of the 210,000 documents require a level 1 review (privilege and relevance). That number will go up or down depending upon the type of business and the similarity between matters. Naturally, more savings can be realized through use of contract attorneys managed by outside counsel. Needless to say, there can be another 30% reduction in overall cost in matter #3.

This approach assumes that the corporation controls the process – retains control of access to the hosted document repository from which all documents are reviewed and decisions as to the individual items are maintained there. Document notes, tags and work product together with logins and credentials for outside counsel users are controlled and managed by the corporation.

Service	Volume (GB)	Doc Count	Cost
Data Collection	20	300,000
Process and Filter	20	300,000	$7,200
Filtered Data	14	210,000
Previously Produced	(These documents can be produced without review)	81,900
Attorney Review		128,100	$256,200
Hosting	14		$6,300
Production (previously produced documents at three cents per page)		165,165	$53,917.50
Total			$324,417.50

A Promise Unrealized

ESI is the product of a technology that changed the face of corporate America. Information Technology has transformed the way we work and live. It has also been the catalyst for every process reengineering initiative in business over the last fifteen years. In companies everywhere each department has been rebuilt from the foundation with astounding end results. There’s just one more department to go. A drastic redesign and reassignment of responsibility for ESI discovery can at last provide the cost savings corporations have longed for.

International Litigation Services, Inc. (ILS)
213.687.7400
http://www.ilsTEAM.com/