Content Analysis for Proactive Intelligence: Marshaling Frame Evidence
Abstract
Modeling and simulation have great potential as technologies capable of aiding analysts in making accurate predictions of future situations to help provide competitive advantage and avoid strategic surprise. However, to make modeling and simulation effective, an evidence-marshaling process is needed that addresses the information needs of the modeling task, as detailed by subject matter experts. We suggest that such an evidence-marshaling process can be obtained by combining natural language processing and content analysis techniques to provide quantified qualitative content assessments, and describe a case study on the acquisition and marshaling of frames from unstructured text.
Cite
Text
Sanfilippo et al. "Content Analysis for Proactive Intelligence: Marshaling Frame Evidence." AAAI Conference on Artificial Intelligence, 2007.Markdown
[Sanfilippo et al. "Content Analysis for Proactive Intelligence: Marshaling Frame Evidence." AAAI Conference on Artificial Intelligence, 2007.](https://mlanthology.org/aaai/2007/sanfilippo2007aaai-content/)BibTeX
@inproceedings{sanfilippo2007aaai-content,
title = {{Content Analysis for Proactive Intelligence: Marshaling Frame Evidence}},
author = {Sanfilippo, Antonio and Cowell, Andrew J. and Tratz, Stephen and Boek, A. M. and Cowell, Amanda K. and Posse, Christian and Pouchard, Line C.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2007},
pages = {919-924},
url = {https://mlanthology.org/aaai/2007/sanfilippo2007aaai-content/}
}