Email this Article Email   

CHIPS Articles: SPAWAR Innovator Develops Automated Capabilities to Analyze Human Language and Social Interactions

SPAWAR Innovator Develops Automated Capabilities to Analyze Human Language and Social Interactions
By DON Innovation - January-March 2017
Dr. Lucas Overbey is a research engineer in the Basic and Applied Sciences Competency at Space and Naval Warfare Systems Center (SPAWARSYSCEN) Atlantic. He is the lead for the SPAWARSYSCEN Atlantic Analytics Research Center (ARC) and has been the principal investigator on multiple ongoing and previous data analytics projects.

As a leading data analytics innovator, Dr. Overbey has contributed greatly to basic and applied research and workforce development. Supported by the Naval Innovative Science and Engineering (NISE) program, he conceptualized and led the establishment of the SPAWARSYSCEN Atlantic ARC.

The ARC is a collaborative Center of Excellence created with the goal of bringing together researchers from computer science, statistics, mathematics, psychology, sociology, and engineering disciplines to jointly write proposals, support and coordinate training in relevant subject areas, hold topical seminars, and allow members to present their current work for review and feedback by other ARC members.

Dr. Overbey proposed and was awarded NISE funds to research new approaches to automatic analyses of social media data with a focus on extracting relevant geographic information. Focusing primarily on Twitter, he developed a novel approach to automatically extracting precise information using message content and social connections between users.

Dr. Overbey’s research also led to the development of several related innovative natural language processing and network analytic capabilities, including sentiment analysis, entity extraction, topic modeling, mixed-language parsing, and identification of influencers. His research is now in the process of being transitioned to United States European Command and United States Marine Corps Intelligence. His projects, as they are implemented, will greatly improve a primarily manual analysis process by filtering task-pertinent information and turning data into actionable knowledge. This automation will increase efficiency and allow people to focus on inherently human tasks.

Dr. Overbey’s work also carries a number of operational implications. One is the capability to identify early indicators of significant human events—such as social unrest—through open source and social media information. Another implication is the ability to automate a measure of public opinion in social media and open source information world wide. Analysts will be assisted by new automated capabilities in their efforts to identify actors or users of value in social media before engaging with them. In addition, data provided to these analysts will be given enhanced capabilities for search, geographic analysis, and key phrase and entity identification and resolution.

The data analytics capabilities of the Navy have been greatly enhanced by Dr. Overbey’s efforts. He was critical to the creation of the SPAWARSYSCEN Atlantic ARC and to foundational advancements in operationally applicable text and social network analysis. His accomplishments in the areas of technical excellence as well as his direct support in the professional mentorship of others within his organization are an exceptional value to the Department of the Navy.

Click here for more information about the SPAWAR ARC.

Join DON Innovation on https://www.facebook.com/NavalInnovation or @DON_Innovation or visit the SECNAV/DON Innovation website at http://www.secnav.navy.mil/innovation/Pages/Home.aspx

Related CHIPS Articles
Related DON CIO News
Related DON CIO Policy

CHIPS is an official U.S. Navy website sponsored by the Department of the Navy (DON) Chief Information Officer, the Department of Defense Enterprise Software Initiative (ESI) and the DON's ESI Software Product Manager Team at Space and Naval Warfare Systems Center Pacific.

Online ISSN 2154-1779; Print ISSN 1047-9988
Hyperlink Disclaimer