Using Adversary Text to Detect Adversary Phase Changes
Abstract
The purpose of this work was to help develop a research roadmap and small proof of concept for addressing key problems and gaps from the perspective of using text analysis methods as a primary tool for detecting when a group is undergoing a phase change. Self-organizing Map (SOM) techniques were used to analyze text data obtained from the world-wide web. Statistical studies indicate that it may be possible to predict phase changes, as well as detect whether or not an example of writing can be attributed to a group of interest.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 10, 2009
- Accession Number
- ADA541020
Entities
People
- Adele B. Doser
- Ann E. Speed
- Christina E. Warrender
Organizations
- Sandia National Laboratories