Session Title: More Text Analytics

Importance of the Topic

There are many tools that can be developed for analyzing text, audio, images, video and more. It is important to have a general understanding of capabilities so that research questions can be posed for reasonable analysis. This session will introduce you to several applications that can be used to spark interest and to think of other potential applications. In this session, we will describe some work we performed with synonyms, the creation of a synonym network, the usage of this network for tracking concepts across a document. We will also look at the flows for topic modeling and entity extraction.

Focus of the Topic

Upon completion of this session, participants will:

Be able to track concept usage across a document
Be able to perform topic modeling on a collection of documents
Be able to use data from entity extraction in several different displays (timelines, maps, graphs)

Format of the Session

Presentation
Demonstration
Learning Exercise
Discussion Questions
Summary and Review

Presentation

Slides can be found at 4-More-Text-Analytics.pptx

Demonstration

Entity Extraction for timelines, maps, and social networks
Emotion Tracking
Concept Tracking

Learning Exercises

Open the flow for tracking concepts
- Modify the flow to load your data
- Modify the flow to track concepts of interest to you
  *Open the flow for for topic modeling
- Modify the flow to load your data
- Review the results and decide if there are modifications that you need to make.
  - For instance, maybe you also want to look at verbs.
Open one of the flows for entity extraction
- Modify the flow to load your data
- Review the results and decide if there are modifications that you need to make.
  - For instance, maybe you want to modify the entity types that are extracted.

More Text Analytics 2011