IA Summit 2017 has ended
Learn More  |  Register  |  Sponsor  |  Join Mailing List  |  Follow Us on Twitter

Pre-conference Workshops: Wednesday, March 22 & Thursday, March 23, 2017
Main Conference: Friday, March 24 - Sunday, March 26, 2017 
Back To Schedule
Wednesday, March 22 • 9:00am - 5:00pm
Deep Text: Using Text Analytics to Create New Ways to Structure and Access Information ($650)

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
NOTE: This workshop has a FEE of $650. To attend, you must register for the workshop. You can do this when you register for the conference or at a later date.

Workshop Description:
Deep Text is a multidimensional approach to text analytics that opens up new ways of organizing and utilizing information. So called unstructured text is actually poly-structured text and Deep Text can discover and create structures that range from traditional taxonomic structures to dynamic clusters of co-occurring terms to views of dynamically defined “sections” of documents. It is an approach that can open up new opportunities for information architecture by providing a rich set of tools.

This workshop will take attendees through the entire process of creating a text analytics platform from how to select the right software for your organization, what resources you will need, how to make the business case, how to develop taxonomies and categorization catalogs or adapt existing information structure resources.

It will also cover a basic iterative development process and a range of types of applications that can be built on this platform. The applications include search, eDiscovery, Business Intelligence, Social Media and Sentiment Analysis and such advanced applications such as Fraud Detection (documents with lies tend to have different word patterns) and distinguishing customers likely to cancel from those merely threatening. We will include multiple case studies of the most exciting new applications and approaches.

Participants will get two major sets of hands-on exercises: developing categorization rules with both pre-selected content and content that they bring to the workshop. The second set of exercises will consist of mapping the techniques covered in the workshop to potential applications that reflect their current needs.

This workshop is based on the recently published book, Deep Text: Using Text Analytics to Overcome Information Overload, Get Real Business Value from Social Media, and Add Big(ger) Text to Big Data


  • Deep understanding of full range of text analytics software, development, and applications - what works and what does not work. 

  • How text analytics can enrich information architecture and how information architecture can lead to new types of applications that utilize text.

avatar for Tom Reamy

Tom Reamy

Founder, KAPS Group
Tom Reamy is the founder of KAPS Group, a group of text analytics and taxonomy consultants and has 20 years of experience in information projects of various kinds.  He has published a number of articles in a variety of journals, and is a frequent speaker at knowledge management... Read More →

Wednesday March 22, 2017 9:00am - 5:00pm PDT