Session Title: Text Analytics Overview

Importance of the Topic

Text Analytics are important to any humanities scholars who are interested in increasing the efficiency of their efforts or exploring new research questions that are difficult to do without technology. This session will provide an overview of text analytics including part of speech tagging and other natural language processing tasks. We will look at example applications of feature comparisons (with Dunning Loglikelihood), clustering or topic modeling, frequent pattern analysis and entity extraction.

Focus of the Topic

Upon completion of this session, participants will understand:

What Text Analytics can do
- Natural language processing capabilities
- Text mining algorithms (feature comparison, clustering or topic modeling, frequent patterns and entity extraction)

Format of the Session

Presentation
Demonstration
Learning Exercise
Discussion Questions
Summary and Review

Presentation

Slides can be found at http://dev-tools.seasr.org/confluence/display/Outreach/Presentations
Link to NLP POS tags at http://code.google.com/p/universal-pos-tags/source/browse/trunk/en-ptb.map?spec=svn2&r=2

Demonstration

SEASR Community Hub
- Natural language processing tasks

Learning Exercises

Open browser to http://seasr.org
- Click on "Community Hub"
- Click on "Keyword Cloud"
- Click on "NLP" to explore the sample flows that have been constructed to demonstrate text processing capabilities

Attendee Project Plan

Review and update project plan
Identify data set to use
Identify analysis to use
Modify and develop the project plan over the week

Discussion Questions

Identify and discuss three other text tools that could be useful in the Humanities?
What are the obstacles to using this technology for text analysis - what will your colleagues say?

Text Analytics Overview 2011