Tag Archives: discovery

March 28, 2017 · 8:25 AM

Key to Improving Predictive Coding Results: Effective ECA

Predictive Coding, when correctly employed, can significantly reduce legal review costs with generally more accurate results than other traditional legal review processes. However, the benefits associated with predictive coding are often undercut by the over-collection and over-inclusion of Electronically Stored Information (ESI) into the predictive coding process. This is problematic for two reasons.

The first reason is obvious, the more data introduced into the process, the higher the cost and burden. Some practitioners believe it is necessary to over-collect and subsequently over-include ESI to allow the predictive coding process to sort everything out. Many service providers charge by volume, so there can be economic incentives that conflict with what is best for the end-client. In some cases, the significant cost savings realized through predictive coding are erased by eDiscovery costs associated with overly aggressive ESI inclusion on the front end.

The second reason why ESI over-inclusion is detrimental is less obvious, and in fact counter intuitive to many. Some discovery practitioners believe as much data as possible needs to be put through the predictive coding process in order to “better train” the machine learning algorithms. However this is contrary to what is actually true. The predictive coding process is much more effective when the initial set of data has a higher richness (also referred to as “prevalence”) ratio. In other words, the higher the rate of responsive data in the initial data set, the better. It has always been understood that document culling is very important to successful, economical document review, and that includes predictive coding.

Robert Keeling, a senior partner at Sidley Austin and the co-chair of the firm’s eDiscovery Task Force, is a widely recognized legal expert in the areas of predictive coding and technology assisted review.  At Legal Tech New York earlier this year, he presented at an Emerging Technology Session: “Predictive Coding: Deconstructing the Secret Sauce,” where he and his colleagues reported on a comprehensive study of various technical parameters that affect the outcome of a predictive coding effort.  According to Robert, the study revealed many important findings, one of them being that a data set with a relatively high richness ratio prior to being ingested into the predictive coding process was an important success factor.

To be sure, the volume of ESI is growing exponentially and will only continue to do so. The costs associated with collecting, processing, reviewing, and producing documents in litigation are the source of considerable pain for litigants. The only way to reduce that pain to its minimum is to use all tools available in all appropriate circumstances within the bounds of reasonableness and proportionality to control the volumes of data that enter the discovery pipeline, including predictive coding.

Ideally, an effective early case assessment (ECA) capability can enable counsel to set reasonable discovery limits and ultimately process, host, review and produce less ESI.  Counsel can further use ECA to gather key information, develop a litigation budget, and better manage litigation deadlines. ECA also can foster cooperation and proportionality in discovery by informing the parties early in the process about where relevant ESI is located and what ESI is significant to the case. And with such benefits also comes a much more improved predictive coding process.

X1 Distributed Discovery (X1DD) uniquely fulfills this requirement with its ability to perform pre-collection early case assessment, instead of ECA after the costly, time consuming and disruptive collection phase, thereby providing a game-changing new approach to the traditional eDiscovery model.  X1DD enables enterprises to quickly and easily search across thousands of distributed endpoints from a central location.  This allows organizations to easily perform unified complex searches across content, metadata, or both and obtain full results in minutes, enabling true pre-collection ECA with live keyword analysis and distributed processing and collection in parallel at the custodian level. To be sure, this dramatically shortens the identification/collection process by weeks if not months, curtails processing and review costs from not over-collecting data, and provides confidence to the legal team with a highly transparent, consistent and systemized process. And now we know of another key benefit of an effective ECA process: much more accurate predictive coding.

Leave a comment

Filed under ECA, eDiscovery

Tagged as , , , , , , , , , ,

July 21, 2015 · 8:47 AM

X1 Social Discovery Available as a Hosted Solution

icons_social_media2X1 Social Discovery is the leading social media and website collection, preservation, and ECA tool on the market.  Customers love it for many reasons:

  • Defensibility: MD5 hash values of individual items are calculated upon capture and maintained through export. Automated logging and reports are generated. Key metadata unique to social media & web streams are captured through deep integration with APIs provided by the publishers. This metadata is important to establishing chain of custody and also provides key evidence relevant to the substantive case as well as authentication.
  • Ease of use: Investigators can take advantage of the patented X1 Search interface that allows fast-as-you-type search, filtering on metadata, and full-fidelity preview of content to quickly find the information of interest.
  • Speed and Scalability: Collect up to hundreds of thousands of items in a single case on an automated basis and search across all the items with lightning fast speed.. Screen shots not only lack defensibility but are far more cumbersome and time consuming.
  • Ease of production: Lawyers love X1 Social Discovery because it fits the litigation workflow perfectly and exports data directly into downstream review tools.  Other customers like the flexible output options such as PDF, native files, or CSV.

To date, X1 Social Discovery has been available only as a local desktop installation.  This works great for customers like law enforcement agencies that need to maintain local possession of evidence by law.  Many law firms and insurance companies we speak with, however, yearn for a hosted solution either because they do not want to manage the huge volume of social media that will be collected or because they are not allowed to possess the content locally.  The latter comes up with many law firms that have made the decision to outsource all evidence handling to service providers, for example, for policy, ethical and cost reasons.

Now, X1 is partnering with D4 and Duff & Phelps to make Social Discovery available on a hosted basis.  This has numerous benefits:

  • Economies of scale on data hosting from cloud providers
  • Do-it-yourself capabilities along with the X1 expertise available from these premier X1 partners
  • Per-matter pricing that allows customers to account for costs by matters (which can be very important to customers like law firms that need to pass through per-matter costs)

In practice, the process is very simple – X1 Social Discovery (which is very deployable in physical, virtual or cloud environments) is stood up in a hosted environment by a service provider. An instance of X1 Social is dedicated to a single case.  The service provider hosts and manages the data, allowing the customer a more economical method of manaing the storage of what can be a high-volume data type.

The highly-respected law firm Lewis Brisbois is taking advantage of this capability early and will be briefly discussing these advantages in tomorrow’s webinar about the importance of social media in litigation.  Already, there are over 800 registrants for this hot topic event.  Attending is a chance to learn how to be ready to handle social media in eDiscovery, as well as why a hosted option can be the right fit.  To join the webinar, click here.

If you would like to talk through the hosted capability further and learn more about the workflow, you can email me directly.

Leave a comment

Filed under SaaS, Social Media Investigations, Social Media Metadata

Tagged as , , , , , , , , , , , , , ,

April 27, 2015 · 10:35 AM

Judges Believe Social Media will Have Biggest Effect on eDiscovery Over the Next Two Years

The good folks at Exterro recently released a very interesting report titled “Federal Judges Survey, eDiscovery Best Practices and Trends.”  The title includes a link to download the report, which I highly recommend reading as it is good to know what the judges who rule on eDiscovery all the time are thinking.  Overall, the report calls for some necessary disruptive change in the practice of eDiscovery in order to demonstrate competency.  There are some excellent tips in the report on how eDiscovery professionals can improve and what kinds of trends we should be on the lookout for.

One finding stood out to me in particular – the Judges surveyed felt that social media would be the technology trend with the biggest effect on eDiscovery over the next two years.

Exterro Survey

As the report states, “Attorneys must be aware that all emerging technology platforms are just like email; if they hold relevant evidence you are accountable for preserving the data.”  At X1, we’ve known this for quite some time.  We’ve blogged about cases where the old way of doing social discovery – print screen – has been shown to lack authenticity standards and not meet the duty of competency that lawyers must meet.  To see the Judges recognize this as a critical trend rather than just a niche corner of the market validates what we have known for years.

It is no coincidence that X1’s Social Discovery product continues its rapid upward trajectory.  There is simply no other product on the market that offers a true investigative platform for this critical new data type.  Such a social media investigative platform will include:

  • Tight API connections to the major social media publishers like Facebook, LinkedIn, Twitter, and Instagram. The API connection allows for the capture of unique metadata that each publisher adds to its data.
  • A web crawler and capture capability that creates a copy of the page to be stored for processing into a preservation repository.
  • The ability to keep data forensically sound. This requires calculating MD5 hash values of individual items upon capture and maintaining those values through export. The platform must keeps logs and reports of all actions on data. It also must be able to use metadata to establish chain of custody and authentication.

The challenge with social media – unlike email – is that much of the data resides outside the walls of an organization.  Collection of social media becomes a challenge. Companies cannot simply call Facebook or Twitter and request all of the information for various custodians.  It is possible to take screenshots of various web pages or social media sites, but as case law points out, screenshots are not necessarily admissible as evidence.  Plus, screenshots take a technical toll on eDiscovery – they can be difficult to index and may require OCR, which still may not be able to pull text out of the image.  That is where an investigative platform like X1 Social Discovery is so important to a competent eDiscovery practice.

2 Comments

Filed under Best Practices, Social Media Investigations

Tagged as , , , , , , , , , , , , , , , ,

March 11, 2014 · 8:51 AM

X1 First To Offer Social Discovery Certification

by Barry Murphy

Education, training, and certification programs are foundational elements of any profession.  When it comes to relatively new functions like social media discovery, the importance of good training and certification options is amplified.  There is a dearth of expertise coupled with the need for corporations and law firms to address challenges quickly – that combination creates an immediate need for formal and effective training.

The activities within the eDiscovery profession tend to be specialized.  For example, forensic disk imaging requires a specific skill set that is very different from the skill set required to run predictive coding review workflows and projects.  As a result, generic eDiscovery certifications have yet to gain mainstream traction in a meaningful way.  This is not to say such programs are not valuable; they are.  However, given the lack of a standards board or independent third-party that has published a treatise on what it means to be qualified to perform “eDiscovery,” it is difficult for any one certification to be an industry standard.  Further, the eDiscovery profession is a sum of many tasks, most of which are performed by various team members (as opposed to one person being responsible for, or capable of performing, all).  What I hear from eDiscovery professionals when it comes to certification is that there is simply not enough definition as to what it means to be a certified eDiscovery professional.

One type of certification that is more important than ever is vendor-specific (or tool-specific) certification.  Previous eDJ Group research had validated the fact that training and education programs are critically important for the practice of eDiscovery.

Vendor certifications

Click on image to enlarge

For years, it has been critically important that forensic investigators be certified on the tools they use – such as Guidance Software’s Encase (EnCE, EnCEP) or AccessData’s FTK (ACE).  Likewise, the Relativity Certified Administrator credential (RCA) from kCura has gained significance in the hosting and review market.  As such, upon joining X1, I was very pleased to hear that the company will offer certification for our X1 Social Discovery tool.  Why is certification for the Social Discovery tool so important?  First, social media is now ingrained in our business lives.  eDJ Group research from September 2013 shows that almost two-thirds of workers now use external social networks like Facebook or LinkedIn for business purposes.

Social Media Part of Business

Click on image to enlarge

Second, social discovery is still fairly new and requires in-depth training.  With X1 Social Discovery, users need to understand how MD5 hash values of individual items are calculated upon capture and maintained through export. They need to understand the automated logging and reports that are generated. They need to be educated on the key metadata unique to social media & web streams that are captured through deep integration with APIs provided by the sites and how this metadata is important to establishing chain of custody and authentication.  Given these new challenges, a certification program just makes sense.  Even better, X1’s Social Discovery tool will be the only one on the market with a certification program in place.  That will be an important distinction in the market, especially given the large amount of law enforcement customers for the product (doing things by the book is extremely critical in law enforcement investigations).

The X1 Social Discovery Certification course, offered by DigitalShield, will cover:

  • Introduction to the foundational skills and knowledge needed to understand social media collection, analysis, review and delivery
  • Best practices for locating and collecting social media
  • Providing investigators, digital forensic examiners and eDiscovery practitioners with the technical skills to use X1 Social Discovery
  • Hands-on training using X1 Social Discovery to collect, manage, and analyze data from Twitter, YouTube, Facebook, webmail and websites

To sign up for the training or to learn more, click here >  

______________________________________________________________________

1 Comment

Filed under Social Media Investigations, Training and Certification

Tagged as , , , , , , , , , , , , , , , ,

May 8, 2012 · 9:14 AM

Social Media Case Law Update: Volume of Cases Accelerating

Recently our survey of published case law from 2010 and 2011 identified 689 cases involving social media evidence for that time period.  While these results exceeded our expectations, that pace is actually rapidly accelerating in 2012. For this past April alone, a quick tally identifies 61 cases where social media evidence played a key role. We will have a mid-year report in a few months, but it appears that the volume of cases has about doubled year over year. Keep in mind that the survey group only involves published cases on Westlaw. With less than one percent of total cases resulting in published opinions, and considering this data set does not take into account internal or compliance investigations or non-filed criminal cases, we can safely assume that there were tens of thousands more legal matters involving social media evidence that were adjudicated or otherwise resolved in April 2012.

The following are brief synopses of three of the more notable social media cases from April:

Blandv. Roberts, 2012 WL 1428198 (E.D.  VA, Apr. 24, 2012)  

This case is notable in that it extensively litigated the implications of “liking” specific items on Facebook.  In this situation the Hampton, Virginia Sheriff’s Office employed Bland and his co-workers, under Sheriff B.J.  Roberts. Roberts faced a contested election and Bland and his cohorts backed the challenger Jim Adams, going so far as to “like” Adam’s Facebook page. As it turned out, the plaintiffs “liked” the wrong horse. Roberts won the election, and he subsequently fired Bland and the other Adams-backers. The Sheriff justified the terminations on cost-cutting grounds, but plaintiffs argued that their termination violated their First Amendment rights, as Roberts was aware that the plaintiffs’ “liked” Adam’s Facebook page, which plaintiff’s asserted to be protected speech. The court ultimately determined that “merely ‘liking’ a Facebook page is insufficient speech to merit constitutional protection and thus the termination was lawful.

From our perspective, the ultimate outcome of Bland v. Roberts is not so much the point as is plaintiffs’ subtle activity on Facebook representing substantive facts of the case.  The act of liking a Facebook entry can be an important piece of evidence in a wide variety of litigation and investigation scenarios. Just to identify a few possible examples, it can constitute evidence toward a party’s knowledge of a particular fact, or the extent of trademark infringement or publication of defamatory material, or identify relevant witnesses in a case. This case illustrates why it is important to collect and preserve all available information on Facebook and other social media sites in a thorough manner with best-practices technology specifically designed for litigation purposes.

People v. Harris, 2012 WL 1381238 (N.Y. Crim. Ct. Apr. 20, 2012)

In this case, the defendant faced charges of disorderly conduct after marching onto the Brooklyn Bridge as a participant in the Occupy Wall Street protests.  The New York District Attorney’s Office subpoenaed Twitter, Inc., seeking user information and Tweets from a particular time period for the Twitter account @destructuremal—the account allegedly used by the defendant.  The defendant filed a motion to quash the subpoena.

In denying the defendant’s motion, the court relied heavily on the public nature of Twitter and its terms of service, which establish that users have no expectation of privacy and no proprietary interest in their Tweets. The court noted that the terms of service state that by submitting a post or displaying content, a user has granted Twitter “a worldwide, non-exclusive, royalty-free license to use, copy, reproduce, process, adapt, modify, publish, transmit, display and distribute such Content in any and all media or distribution methods (now known or later developed).”  Thus, the court reasoned, “defendant’s inability to preclude Twitter’s use of his Tweets demonstrates a lack of proprietary interest” in them.  In assessing the Plaintiff’s privacy rights, the court again relied on Twitter’s Terms of Service, which clearly inform users that their information will be viewable by others and which specifically state that “[w]hat you say on Twitter may be viewed all around the world instantly … [t]his license is you authorizing us to make your Tweets available to the rest of the world and to let others do the same.”

Loporcaro v. City of New York and Perfetto Contracting Company,  35 Misc.3d 1209(A), (N.Y. Sup. Ct. Apr. 9, 2012)

This is yet another serious personal injury claim where the claimant’s public Facebook postings contradicted their assertions of serious injury. Plaintiff claimed permanent disability from two knee injuries while on the job as a firefighter, seeking redress against Perfetto Contracting Company, Inc., alleging defective road conditions caused his injury. However, his public Facebook postings suggested that he continued to maintain an active lifestyle. This prompted the court to grant the defense’s motion to compel production of the Plaintiff’s full Facebook account, ruling as follows:

“When a person creates a Facebook account, he or she may be found to have consented to the possibility that personal information might be shared with others, notwithstanding his or her privacy settings, as there is no guarantee that the pictures and information posted thereon, whether personal or not, will not be further broadcast and made available to other members of the public. Clearly, our present discovery statutes do not allow that the contents of such accounts should be treated differently from the rules applied to any other discovery material, and it is impossible to determine at this juncture whether any such disclosures may prove relevant to rebut plaintiffs’ claims regarding, e.g., the permanent effects of the subject injury. Since it appears that plaintiff has voluntarily posted at least some information about himself on Facebook which may contradict the claims made by him in the present action, he cannot claim that these postings are now somehow privileged or immune from discovery.”

Earlier this year we covered the case of Tompkins vs. Detroit Metropolitan Airport, which also highlighted the importance of systematic search of public Facebook as standard procedure for nearly every type of criminal and civil litigation investigation.

We will have an update in about four weeks for the social case law published in May, so stay tuned.

4 Comments

Filed under Best Practices, Case Law

Tagged as , , , , , , , , , , , , , , , ,