Charles River Analytics looks to help the Department of Defense enhance organizational effectiveness through a new analytical technology that employs artificial intelligence to generate insights from free-form text.
CRA said Tuesday its new sentiment analysis technique named the Jargon Association for Language Analysis in Domains harnesses natural language processing and best practices in human-machine interface design to provide defense organizations with personnel insight.
JALAD consists of a jargon discovery tool, an intuitive user interface and a model designed for decoding the text data.
The jargon discovery and semantic association tool matches defense terms with data from a DOD dictionary via machine learning algorithms and statistical techniques. JALAD’s model then uses neural networks to run a sentiment analysis to make the text data understandable.
The intuitive user interfaces are tailored to suit the needs of specific users, such as analysts and commanders.
Scientists at Charles River hope JALAD can help the Defense Equal Opportunity Management Institute and the Defense Human Resources Activity assess personnel.
“JALAD is exciting because we’re allowing the large amount of feedback from across the DOD to be heard and understood by the DEOMI, so that they can promote increased diversity, inclusion and equal opportunity,” said Ceara Chewning, JALAD principal investigator at CRA.