Predictive Analytics World for Government


Making Text Mining Work: Practical Methods and Solutions

October 20, 2016

Intended Audience: Practitioners seeking tools to analyze unstructured text data.
Program Level: Intermediate
Recommend Field of Study:
   • Computer Science
   • Analytics
   • Statistics
   • Mathematics
   • Finance and Marketing

A free copy of Dr. Fast's book on Practical Text Mining is included.

Register Now

Workshop Description

In their 2011 Hype Cycle report, Gartner has Text Analytics sliding into the "Trough of Disillusionment", highlighting the difficulty of achieving its great promise. Despite this verdict, text mining and text analytics can be valuable tools, if you know where to look for the solution. This workshop will address:

  • The text mining solutions available now and the problems for which they are best suited
  • Best practices in the key text mining areas
  • How to set positive but realizable expectations for the return on investment of a text mining project

This one-day session surveys standard and advanced methods for text mining. Dr. Fast will describe the key inner workings of leading algorithms, demonstrate their performance with business case studies, compare their merits, and show how to pick the approach best suited for your project. Methods covered include search indexes, text classification, information extraction, document similarity and more.

The key to successfully leveraging these methods is to find the right "hammer" for your text "nails" and understand the limits of those techniques.

Dr. Fast will share his experience mining text on real-world applications in several fields, highlighting the range of available solutions and how to combine technologies to maximize the value of the vast store of (untapped) unstructured data.

About the Presenter


Chief Scientist Dr. Andrew Fast leads research in Text Mining and Social Network Analysis at Elder Research, the nation's leading data mining consultancy. Dr. Fast graduated Magna Cum Laude from Bethel University and earned Master's and Ph.D. degrees in Computer Science from the University of Massachusetts Amherst. There, his research focused on causal data mining and mining complex relational data such as social networks. At Elder Research, Andrew leads the development of new tools and algorithms for data and text mining for applications of capabilities assessment, fraud detection, and national security.

Dr. Fast has published on an array of applications including detecting securities fraud using the social network among brokers, and understanding the structure of criminal and violent groups. Other publications cover modeling peer-to-peer music file sharing networks, and understanding how collective classification works.

  Register Now