Accelerating Exploitation of Low-grade Intelligence through Semantic Text Processing of Social Media
Abstract
Social media will play a key role in many areas of intelligence operations with the development of knowledge extraction analytics. The data contained within these social networking services present many challenges, but the value obtained from detecting subtle and hidden information exchanges and environmental observations are vast. The analytics that will drive social media knowledge exploitation include advanced text processing technologies allowing multi-faceted concept or frame-based queries within a familiar search engine interface for users who are not expert analysts or who may be operating with limited intelligence resources in disadvantaged information collection situations. In this paper, we demonstrate constructing frame-based semantic search queries using models of concepts and roles extracted from social media content. This approach to searching allows intuitive query formulations requiring less up-front knowledge of the search parameters. We demonstrate this semantic search capability by querying over seven million tweets captured during the Arab Spring uprisings.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2013
- Accession Number
- ADA587022
Entities
People
- Sue E. Kase
Organizations
- United States Army Research Laboratory