Close
Enter your
text here

Industry Trends

Tuesday’s ILTACON Sessions: eDiscovery Trends

As noted yesterday, the International Legal Technology Association (ILTA) annual educational conference of 2015 (now known as ILTACON) is happening this week and eDiscovery Daily will be reporting this week about the latest eDiscovery trends being discussed at the show.  There’s still time to check out the show if you’re in the Las Vegas area with a number of sessions available and over 190(!) exhibitors providing information on their products and services.

Perform a “find” on today’s ILTACON conference schedule for “discovery”, “litigation support” or “information governance” and you’ll get at least 4 sessions with hits (including this one where I’ll be presenting, for a whopping six minutes).  So, there is plenty to talk about!  Sessions in the main conference tracks include:

11:00 AM – 12:00 PM:

Successfully Selling an Information Governance Program

Description: What is the secret to selling the idea of implementing an information governance program at your organization? A panel of experts will discuss the business drivers relevant to getting people on board, including key indicators of success.

Speakers are: Beth Chiaiese, CRM – Foley & Lardner LLP; Rudy Moliere – Morgan, Lewis & Bockius, L.L.P.; Sharon Keck – Polsinelli PC.

To Share Or Not To Share: The Debate Over Disclosure of E-Discovery Protocols

Description: What do you have to tell opposing counsel about your search, culling and review strategies? What if they object? What do courts say about these issues? Litigation support professionals will hear a thought-provoking discussion between Judge Andrew Peck and a panel of lawyers with differing views about the delicate balance between cooperation and advocacy.

Speakers are: Patrick L. Oot – Shook, Hardy & Bacon L.L.P.; Julie M Richer – American Electric Power Legal Department; Honorable Andrew J Peck; Mr Philip Favro – Recommind, Inc.; Alex Ponce de Leon – Google Inc. Legal Department.

1:30 PM – 2:30 PM:

20 E-Discovery Warnings in 60 Minutes

Description: We’ve all been there: Things don’t go as expected, and you end up getting burned. Join your peers in this interactive session where audience members will provide examples of things that went awry and, more importantly, how the issue was resolved. Attendees will walk away with some great tips to avoid future fire drills!

Speakers are: Michael Boggs – Holland & Hart; George J. Socha – Socha Consulting.

3:30 PM – 4:30 PM:

Building Strategic Litigation Support Relationships

Description: Trying to accomplish things on your own could take more resources than you have, and you might not generate the best results. The best strategic relationships don’t just happen, but what does it take to develop and maintain the optimal strategic relationship? Panelists will share techniques they have used to nurture and maintain their strategic relationships and how the investments have paid off. Gain insight on building and maintaining strategic relationships in your litigation support organization.

Speakers are: Greg Anderson – Lateral Data, A Xerox Company; Doug Matthews – Vorys, Sater, Seymour and Pease LLP; Donna Epes – Qdiscovery; Joe Turner – Lateral Data, A Xerox Company; Geoff Wilcox – UnitedLex.

For a complete summary listing of all sessions at the conference, click here.

So, what do you think?  Are you planning to attend ILTACON this year?  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

Welcome to ILTACON 2015!: eDiscovery Trends

The International Legal Technology Association (ILTA) annual educational conference of 2015 (now known as ILTACON) kicked off yesterday with several networking events, and begins in earnest today with the first day of sessions.  eDiscovery Daily will be reporting this week about the latest eDiscovery trends being discussed at the show.  Over the next four days, we will provide a description each day of some of the sessions related to eDiscovery to give you a sense of the topics being covered.

If you’re in the Las Vegas area, come check out the show – there are a number of sessions available and over 190(!) exhibitors providing information on their products and services.  Perform a “find” on today’s ILTACON conference schedule for “discovery”, “litigation support” or “information governance” and you’ll get at least 6 sessions with hits.  So, there is plenty to talk about!  Sessions in the main conference tracks include:

11:00 AM – 12:00 PM:

Creating the Firm of the Future: Utilizing IG Assessments To Drive Improvements

Description: In a world of ever-rising concerns of privacy, security and protecting intellectual property, clients are now more information savvy, and are insisting that their law firm representation is maintaining high standards when it comes to internal information governance (IG) strategies and practices.

Therefore, the firms of the future will need to able to offer clients proof of where they stand on the maturity of these practices to secure client trust and confidence.

Is your firm ready to answer the call for transparency?

In this session, you will learn how an IG assessment can play a critical role in taking your firm to the Next Level in preparing to meet your clients’ increasing demands and expectations for governing their information.  You’ll understand what it takes to deploy a firm-wide assessment,  and hear about real-world experiences with implementation and leveraging outcomes.

Speaker is: David Vickers – ARMA International

Embracing Managed Services for Litigation Support

Description: Is your firm contemplating a move to a managed services model? Are you wondering what the journey entails? A panel of leaders who have embraced the switch to managed services for litigation support will tell their tales of what led them there, associated costs, staffing, the type and volume of work and, most important, how it is working out.

Speakers are: Wale Elegbe – Sullivan & Cromwell LLP; R.P. Smith – Jones Walker LLP; Chris Haley – Troutman Sanders LLP; Kim C. Edwards – Patterson Belknap Webb & Tyler LLP.

1:00 PM – 2:00 PM:

Building Information Governance Like “Ocean’s Eleven”

Description: In the 2001 movie “Ocean’s Eleven,” George Clooney assembles the perfect team to pull off a spectacular Vegas robbery. In managing IT governance, risk and compliance (GRC), your firm also needs to assemble the perfect team. How do you find and manage the key players in GRC, and how do you properly divide the varied responsibilities that must be shouldered? Together we can figure out how to build a team that prepares us for the heist (GRC program) of a lifetime.

Speakers are: Nancy Beauchemin – InOutsource; Beth A. H. Faircloth – Seyfarth Shaw LLP; Tim Schank – Vedder Price P.C.; Stuart Senator – Munger, Tolles & Olson LLP.

Litigation Support Roundtable

Description: We all hate the fire drills and would like to prepare for challenges before they arrive. What major challenges in litigation support will we face next? During this moderated roundtable discussion of hot topics in litigation support, we will address concerns on the minds of your peers and identify issues to consider for the future. Topics will be selected by session attendees and could include staffing, product selection, technological advances, recent case decisions, outsourcing, etc.

Speakers are: Joanne Lane – Merck & Co., Inc.; Stephen Dooley – Sullivan & Cromwell LLP.

2:30 PM – 3:30 PM:

Information Governance Consulting: Law Firm Opportunity or Mistake?

Description: Driven by information security requirements, e-discovery costs and government regulations, clients are turning to law firms for strategic approaches to managing their information. Law firms have an opportunity to assist and further direct and grow information governance initiatives within client organizations, but what are the risks of this type of work? What do clients expect? What can law firms provide that technology solutions do not, and what benefits come from this type of client relationship? Opportunity or mistake? You make the call!

Speakers are: Brynmor Bowen – Schulte Roth & Zabel; Ms Samantha J Lofton – Ice Miller LLP.

4:00 PM – 5:00 PM:

Is Big Data in Legal a Figment of Our Imaginations?

Description: The big data phenomena simply does not apply to the legal market. After all, our firms’ data sets and data complexities are much too small to warrant industrial-strength big data technologies and techniques, right? This panel of law firm technology, privacy and governance experts strongly disagrees! We will share firsthand examples of big data at work in our law firms and show how to apply “big data thinking” to utilize technologies and techniques in a new, more productive, efficient and analytical way. Get ready for real-time role playing aimed to arm you with the information you need to address your managing partner’s big data questions (and doubts) and build a solid big data business case even the biggest curmudgeon can’t deny. Along the way, our experts will touch on hot themes including technology (analytics, algorithms, etc.) and governance (including privacy and security). We’ll also share enough legal big data (BD) case studies to make BD-lievers out of everyone!

Speakers are: Jobst Elster – InsideLegal.Com; Brynmor Bowen – Schulte Roth & Zabel; Eric Hunter – Bradford & Barthel, LLP; Galina Datskovsky – Vaporstream; Judy Selby – Baker & Hostetler LLP; Paul Starrett – Starrett Consulting and Investigative Services.

For a complete summary listing of all sessions at the conference, click here.

So, what do you think?  Are you planning to attend ILTACON this year?  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

Get Ready for ILTACON!: eDiscovery Trends

It’s a rare Saturday post for us as we get ready for ILTACON 2015, the (newly named this year) annual educational conference for the International Legal Technology Association (ILTA), which will be at Caesars Palace in Las Vegas this year.  It starts tomorrow with several networking events, and begins in earnest on Monday with the first day of sessions.  Just a warning, Caesars Palace is not pager friendly!  Here are a few resources to help you get ready.

Summary Agenda of Networking Events, Educational Sessions, Meals and Breaks, etc.

Summary Grid of Conference Sessions (4 page PDF)

Detailed Conference Session Agenda with Descriptions of the Sessions (61(!) page PDF)

Details on Networking Events and Recreational Events (hey, everybody needs some R&R during a long show!)

Even a one-page PDF with 8 Reasons Why You Should Send Your Hard-Working and Deserving Employee to ILTACON 2015 (to help convince your boss to send you).

eDiscovery Daily will be at the show and will cover the sessions and highlight sessions each day related to eDiscovery, litigation support and Information Governance.  Heck, we will even be presenting at the 20 E-Discovery Warnings in 60 Minutes session on Tuesday at 1:30 (for a whopping six minutes).  Hope to meet you there!

So, what do you think?  Are you attending ILTACON this year?  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

Government Attorneys Are More Confident about eDiscovery But Feel Less Prepared to Discuss It: eDiscovery Trends

In April 2014, we covered the seventh annual benchmarking study of eDiscovery Practices for Government Agencies conducted by Deloitte and covered the eighth annual study last December.  Apparently, Deloitte operates on an eight month year – their Ninth Annual Benchmarking Study of Electronic Discovery Practices for Government Agencies is available now.

This time, one hundred twenty four (149) professionals (up from 124 last time) across multiple government agencies participated in the survey, with attorneys comprising 60% of the respondents (down from 69% last time).  Here are some key findings in the report:

  • Use of predictive coding is on the rise again as 27% of respondents indicated having used predictive coding in any of their cases, up from 23% last year and 17% in the April 2014 results.
  • Collection from mobile devices in eDiscovery is sharply on the rise as 54% of respondents have collected data from smart phones or tablets in their eDiscovery matters, up from 26% last December. 28% of respondents have requested data from mobile sources.
  • Requesting and producing social media data is somewhat low, as only 23% of respondents have requested social media data, such as Facebook, LinkedIn or Twitter from opposing counsel and only 11% have produced social media data from those sites.
  • Individual confidence continues to rise as 85% of respondents felt as confident or more confident in their ability to manage eDiscovery in their cases as compared to a year ago. But, agency confidence is still a concern as 78% of respondents feel somewhat or not at all effective in their agency’s ability to deal with the challenges of eDiscovery and 75% of respondents feel somewhat or not at all confident that if challenged their agency could demonstrate that their ESI was “accurate, accessible, complete, and trustworthy”.
  • When it comes to discussing matters regarding eDiscovery with opposing counsel, the trend is considerably downward as only 42% of respondents felt adequately prepared to do so, down from 56% last time and less than half the percentage as it was in 2012 (when it was 87%). That’s clearly heading the wrong direction.

Once again, these are some sample findings.  For a complete list of findings, available in a condensed, two-page (this time) USA Today style infographic, click here to download.  Twice the pages as last time, but the report is still free!

So, what do you think?  Do you work for, or with, government agencies?  If so, do any of these findings surprise you?  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

Want to Avoid eDiscovery “Gotchas”? Attend this Session at ILTA: eDiscovery Best Practices

There is less than two weeks left before ILTACON 2015, the annual conference for the International Legal Technology Association (ILTA) at Caesars Palace in Las Vegas.  eDiscovery Daily will be at the show and providing coverage before, during and after the show.  If you’re attending (or thinking of attending), here is one session that you should put on your list to check out.

The session 20 E-Discovery Warnings in 60 Minutes will be moderated by George Socha, EDRM co-founder and president of Socha Consulting and Michael Boggs, director of practice support at Holland & Hart.  George and Michael will moderate a fast-paced series of live stories from audience members, who will share examples from their own experiences of eDiscovery situations gone wrong, explain how the issue was ultimately resolved, and share their lessons learned.  As George noted in EDRM’s announcement regarding the session yesterday, “The session will offer 20 opportunities to learn from the mistakes of others – an educational and entertaining way to increase one’s own success rate.”

Several eDiscovery professionals will be presenting the eDiscovery situations gone wrong, including me.  I will be presenting two topics that are issues we have experienced with some of our clients at CloudNine and how we addressed them (hint: we’ve covered them on this blog before).  So, I hope to meet you there!

The session will take place on Tuesday, September 1, from 1:30 to 2:30 pm at the ILTACON 2015 conference at Caesars Palace in Las Vegas (currently slated for Milano Ballroom I & II).

So, what do you think?  Will you be attending ILTACON this year?  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

What’s Better than the Discovery Channel? The eDiscovery Channel!: eDiscovery Trends

Sometimes, I look for blog post ideas in different places, including performing searches for eDiscovery topics on Twitter, which yielded this gem.

If you’ve been a long time follower of this blog (or even not that long), you’re familiar with the thought leader interview series we conduct every year at LegalTech New York (LTNY).  Now, you can listen to podcasts from a couple of eDiscovery thought leaders from the comfort of your own computer!

The site ESI Bytes is a terrific resource for podcasts where top experts share their opinions and tips.  In their latest podcast, Craig Ball and Tom O’Connor about their new eDiscovery podcast series, the eDiscovery Channel.  Craig and Tom discuss various eDiscovery topics with the “sheriff”, the Honorable John Facciola, former United States Magistrate Judge for the United States District Court for the District of Columbia and Karl Schieneman, Founder and President of Review Less.

On this podcast, the topics they discussed included the recent Lola v. Skadden Arps appellate court ruling where the Second Circuit court ruled that the plaintiff’s lawsuit demanding overtime pay from law firm Skadden, Arps and legal staffing agency Tower Legal Solutions can proceed and whether review attorneys are actually performing legal work.  In that vein, they also discussed the quality of manual review and the plight of the attorney reviewer today.  In addition, they also took a look at the case we covered on Monday, United States v. Louisiana, where the defendant originally submitted a 2,941 page privilege log.  Good stuff, from a knowledgeable panel!

Tom previously partnered with the late Browning Marean to co-host the podcast series called the e-Discovery Zone, so you may have enjoyed some of his podcasts in the past.  eDiscovery Channel appears to have been in existence for at least a year, with posts going back as far as last year’s ILTA show at least.  I hope that they will post regularly and get others involved as well, it could be a very unique and beneficial resource to hear unique perspectives directly from well-respected eDiscovery thought leaders!  And, you don’t have to be Naked and Afraid to enjoy it!

So, what do you think?  Are you familiar with ESI Bytes or the eDiscovery Channel?  If not, you should check them out!  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

NIST Issues Draft Guide for “Securing Electronic Health Records on Mobile Devices”: eDiscovery Trends

As we’ve discussed previously, stolen health records are worth a lot in the black market and that was underscored when health insurance provider Anthem announced in early February that it had suffered what appears to be the largest breach ever in the health insurance industry, affecting about 80 million people.  Now, the National Institute of Standards and Technology (NIST) has released a draft guide that might help, at least with regard to securing electronic health record on mobile devices.

On July 23, the National Cybersecurity Center of Excellence (NCCoE), a division of NIST, released a draft of its first cybersecurity practice guide – Special Publication 1800-1: “Securing Electronic Health Records on Mobile Devices”, designed for health IT professionals to use to bolster security for the use of mobile devices in the health care industry.  As discussed in the press release issued by NIST, “Medical identity theft already costs billions of dollars each year, and altered medical information can put a person’s health at risk through misdiagnosis, delayed treatment or incorrect prescriptions.  Yet, the use of mobile devices to store, access and transmit electronic health care records is outpacing the privacy and security protections on those devices.”

The draft guide was developed by industry and academic cybersecurity experts, with the input of health care providers who first identified the challenge. The center then invited technology providers with relevant commercial products to partner with NIST through cooperative research and development agreements and collected public feedback at multiple steps along the way.

The draft guide is comprised of five sections, as follows:

Each section is downloadable separately as a PDF, or you can download a .zip file of all volumes (4.82 MB), plus manifest and template files referred to in SP 1800-1c, from this page.

The comment period will run through September 25.  You can submit comments on the guide through the form on this page or download the spreadsheet template from that page to collect feedback and email the worksheet to HIT_NCCoE@nist.gov.

As I discussed on Monday, potential data breaches can still happen the old fashioned way, via stolen mobile devices.  I was glad my laptop was encrypted when it was stolen last year.  Hopefully, this new guide from NIST can help medical professionals to secure their mobile devices and protect against data breaches on those devices.

So, what do you think?  Do you think this new guide will reduce the number of data breaches within the medical profession?  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

Do You Have a Favorite Law Blog? If So, Now is the Time To Recognize it!: eDiscovery Trends

Once again, ABA Journal is working on their annual list of the 100 best legal blogs, and they would like your advice on which blogs you think they should include.  If you have a favorite law blog (or “blawg”, get it?), now is the time to nominate it for recognition in the ABA Journal Annual Blawg 100.

On their Blawg 100 Amici page, you can complete the form to identify yourself, your employer or law school, your city and email address, the URL of the blog you wish to nominate, a link to a recent post from the blog and a brief (up to 500 characters) description as to why you’re a fan of the “blawg”.  You’re also asked whether you know the “blawgger” personally (and admonished to “be honest”), whether ABA Journal can use your name and comment in their coverage and, if you follow the blogger on Twitter, describe what makes him/her stand out.  You can nominate more than one “blawg”.

ABA Journal notes that they discourage submissions (which they call “amici”) from:

  • Bloggers who nominate their own blogs or nominate blogs to which they have previously contributed posts.
  • Employees of law firms who nominate blogs written by their co-workers.
  • Public relations professionals in the employ of lawyers or law firms who nominate their clients’ blogs.
  • Pairs of bloggers who have clearly entered into a quid pro quo agreement to nominate each other.

Friend-of-the-blawg briefs (i.e., to fill and submit the form) are due by no later than 11:59 p.m. CT on Sunday, Aug. 16, 2015 to include your nomination.

If you have enjoyed reading eDiscovery Daily over the past year and found our blog to be informative, we would love to be recognized!  Feel free to click on the link here to nominate us!  We appreciate the consideration!

There are other excellent legal technology blogs out there.  Here are a few of our favorites.  Feel free to nominate them too.  🙂

For compilations of eDiscovery news and analysis, I’d also like to recognize PinHawk Law Technology Daily Digest and Complex Discovery as excellent sources for eDiscovery information.

Our hats are off to all of those who provide eDiscovery news and analysis to the industry!  Again, if you would like to nominate any of the blogs (including, of course, eDiscoveryDaily), click here.  Deadline is August 16.

So, what do you think?  Do you have a favorite eDiscovery blog or source of information?  Share it with our readers!  And, please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

EDRM Participant Profiles: eDiscovery Trends

When EDRM announced eDiscovery Daily as an Education partner back in March (we covered it here), EDRM agreed to publish our daily posts on the EDRM site and it has been great to publish our content via the leading standards organization for the eDiscovery market!  However, another part of our agreement was for eDiscovery Daily to provide exclusive content to EDRM, including articles sharing real-life examples of organizations using EDRM resources in their own eDiscovery workflows.  Now, our first participant profile is available on the EDRM site and we’re looking for other organizations to share their EDRM experiences!

These profiles are designed to illustrate how participants and their organizations contribute to the success of EDRM as well as how those organizations use EDRM resources in their own businesses.

Our first EDRM Participant Profile Interview is with Seth Magaw. Seth currently serves Ricoh Americas Corporation as Director of eDiscovery Client Services within Ricoh Legal. He is responsible for the development and implementation of service delivery for Ricoh’s electronic discovery hosting services and enhancing the organization’s overall standing in the litigation support industry.  During Seth’s ten years at Ricoh, he has handled many eDiscovery projects, including large forensic collections, ESI and hosting projects. Prior to his current role, Seth has also served Ricoh Legal as Regional Digital Support Project Manager and Digital Sales Analyst.

Ricoh is a global technology and services company and has been a powerful partner to the legal community for more than two decades, earning the trust of clients through experience, expertise and long-term relationships.

In my interview with Seth, he provided some excellent examples of Ricoh’s participation and contributions to EDRM resources and also discussed several of the instances where Ricoh has applied EDRM models and standards within its organization.  Hopefully, the interview with Seth (as well as additional interviews with other EDRM participants to come) will help educate eDiscovery professionals as to how they can use EDRM resources within their own organizations.

The link to Seth’s interview on the EDRM site is here.  I hope you will check it out.

If you are a participant of EDRM and would like to be profiled (or would like to recommend a current EDRM participant to be profiled), please contact George Socha (george@edrm.net), Tom Gelbmann (tom@edrm.net) or me (daustin@cloudnincloudnine.comm) to arrange a profile interview with me to be published on the EDRM site.  We would love for you to share your experiences with EDRM and its resources!

So, what do you think?  Are you an EDRM member and want your organization to be profiled?  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.

This Study Discusses the Benefits of Including Metadata in Machine Learning for TAR: eDiscovery Trends

A month ago, we discussed the Discovery of Electronically Stored Information (DESI) workshop and the papers describing research or practice presented at the workshop that was held earlier this month and we covered one of those papers a couple of weeks later.  Today, let’s cover another paper from the study.

The Role of Metadata in Machine Learning for Technology Assisted Review (by Amanda Jones, Marzieh Bazrafshan, Fernando Delgado, Tania Lihatsh and Tamara Schuyler) attempts to study the  role of metadata in machine learning for technology assisted review (TAR), particularly with respect to the algorithm development process.

Let’s face it, we all generally agree that metadata is a critical component of ESI for eDiscovery.  But, opinions are mixed as to its value in the TAR process.  For example, the Grossman-Cormack Glossary of Technology Assisted Review (which we covered here in 2012) includes metadata as one of the “typical” identified features of a document that are used as input to a machine learning algorithm.  However, a couple of eDiscovery software vendors have both produced documentation stating that “machine learning systems typically rely upon extracted text only and that experts engaged in providing document assessments for training should, therefore, avoid considering metadata values in making responsiveness calls”.

So, the authors decided to conduct a study that established the potential benefit of incorporating metadata into TAR algorithm development processes, as well as evaluate the benefits of using extended metadata and also using the field origins of that metadata.  Extended metadata fields included Primary Custodian, Record Type, Attachment Name, Bates Start, Company/Organization, Native File Size, Parent Date and Family Count, to name a few.  They evaluated three distinct data sets (one drawn from Topic 301 of the TREC 2010 Interactive Task, two other proprietary business data sets) and generated a random sample of 4,500 individual documents for each (split into a 3,000 document Control Set and a 1,500 document Training Set).

The metric they used throughout to compare model performance is Area Under the Receiver Operating Characteristic Curve (AUROC). Say what?  According to the report, the metric indicates the probability that a given model will assign a higher ranking to a randomly selected responsive document than a randomly selected non-responsive document.

As indicated by the graphic above, their findings were that incorporating metadata as an integral component of machine learning processes for TAR improved results (based on the AUROC metric).  Particularly, models incorporating Extended metadata significantly outperformed models based on body text alone in each condition for every data set.  While there’s still a lot to learn about the use of metadata in modeling for TAR, it’s an interesting study and start to the discussion.

A copy of the twelve page study (including Bibliography and Appendix) is available here.  There is also a link to the PowerPoint presentation file from the workshop, which is a condensed way to look at the study, if desired.

So, what do you think?  Do you agree with the report’s findings?  Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by CloudNine. eDiscovery Daily is made available by CloudNine solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Daily should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.