COLLEGE DIRECTORY       :      VISIT ELLER      :      LOG IN 
Eller College of Management
Eller College Home > MIS > Artificial Intelligence Laboratory > Research > Digital Libraries > GetSmart
Artificial Intelligence Laboratory

Digital Libraries Projects - GetSmart

GetSmart - An Integrated DL/Learning Tool

Research Goal

GetSmart is intended to integrate curriculum support, search functions, and knowledge visualization tools in a digital library, learning-oriented environment.

 The National Science Digital Library (NSDL), launched in December 2002, is emerging as a center of innovation in digital libraries as applied to education. As a part of this extensive project, the GetSmart system was created to apply knowledge management techniques in a learning environment. The design of the system is based on an analysis of learning theory and the information search process. Its key notion is the integration of search tools and curriculum support with concept mapping. More than 100 students at the University of Arizona and Virginia Polytechnic Institute used the system in the fall of 2002. A database of more than one thousand student-prepared concept maps has been collected with more than forty thousand relationships expressed in semantic, graphical, node-link representations. Preliminary analysis of the collected data is revealing interesting knowledge representation patterns. 

Return to Top


NSF National SMETE Digital Library: “Intelligent Collection Services for and about Educators and Students: Logging, Spidering, Analysis and Visualization”  Award No. DUE-0121741, Program 7444. September 2001-August 2003.

Return to Top


Related Projects:

  • NSDL

We would like to thank the NSF for supporting this project.

We would also like to thank Rao Shen in Virginia, the GetSmart team and the other members of the Artificial Intelligence Lab at the University of Arizona who developed modules used in this system.

User evaluation surveys have been conducted with the help of Dr. Lillian Cassel

Return to Top

Approach & Methodology

Concept mapping has been identified in many educational psychology studies as a useful technique to enhance learning. Visual node and link semantic graphs have been applied to numerous knowledge-related lines of investigation including: as an assistant tool for individual learning (Novak, 1984), as an evaluation of learning effectiveness (Stanford Education Assessment Laboratory, 1992), as a group communication tool (Trochim, 1989), Organizing hypermedia resources using concept map (Carnot et al., 2000), Online collaboration through concept mapping (Gains et al. 1995), etc

The GetSmart system brings together basic curriculum functions, concept mapping and advanced information retrieval techniques in a web-based learning environment.

Current lines of research include the provision of concept maps as OAI objects, analysis of the relationship of source texts to human-drawn concept maps, and the categorization of human-created link labels into semantically similar link types. One important goal is to support the accumulation of knowledge using matching and merging algorithms and to increase the usefulness of text resources by creating concept maps from text.

Return to Top

Team Members

Dr. Hsinchun Chen
Edward Fox  
Byron Marshall  
Yiwen Zhang  

Return to Top


B. Marshall, H. Chen, T. Madhusudan, "Matching Knowledge Elements in Concept Maps using a Similarity Flooding Algorithm", Decision Support Systems, Vol.42, No.3, Dec 2006, Pages 1290-1306., October 2005

Byron Marshall, Yiwen Zhang, Hsinchun Chen, Ann Lally, Rao Shen, Edward Fox and Lillian Cassel “Knowledge Management and E-Learning: the GetSmart Experience” Presented at the Third ACM and IEEE Joint Conference on Digital Libraries (JCDL-2003), Houston, May 2003.

“Element Matching in Concept Maps”, Byron Marshall, Therani Madhusudan , Accepted, to be presented at the fourth ACM and IEEE Joint Conference on Digital Libraries (JCDL-2004) June 7-11, Tucson, AZ

Return to Top