home · mobile · calendar · defenses · 2008-2009 · 

Thesis Defense - Gu

Personalized Information Seeking to Support Intentional Learning
Qianyi Gu
Computer Science PhD Candidate

To provide the methods for improving the science education, many learning theories have studied on how people acquire knowledge and build up their own scientific understandings. One of the findings is that the learning can be viewed as a learner controlled process in which the learners keep incorporating new knowledge with their previously gained knowledge. With the rapid growth of the internet, many learners go online to find materials they need to achieve their learning tasks. Many educational digital libraries have been developed to provide high quality online educational resources. With the vast amount of online educational resources available, the challenge is to go beyond the ability to locate information and acquire the meaning and gain understandings. Thus, my thesis explores on how to design and implement an intelligent learning services based on the learners' prior knowledge to scaffold the learners effectively using online information resources in digital libraries to improve their scientific understandings.

First, the thesis proposed a collection of scaffolding strategies for the education developers to build up learning services to help the learners to search and effectively use online information resources. To support these strategies, it implemented a personalized information retrieval services based on what learners know and what they should know in their learning process. It also explored using knowledge visualization to improve learning experiences. It implemented a novel algorithm to dynamically generate the customized visualization of knowledge maps and investigated the integration of such visualization with other learning services. A learning study shows that this personalized scaffolding can promote learners to diagnose their own understanding and encourage the learning process with associated metacognitive monitoring. Thus, it is able to support deeper integration of science content with learners' prior knowledge.

Committee: Tamara Sumner, Associate Professor (Chair)
James Martin, Professor
Martha Palmer, Department of Linguistics
Katie Siek, Assistant Professor
Kirsten Butcher, University of Utah
Department of Computer Science
University of Colorado Boulder
Boulder, CO 80309-0430 USA
May 5, 2012 (14:20)