Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form


Zegarra, Emilio (2015) IMPROVING PEER LEARNING AND KNOWLEDGE SHARING IN STEM COURSES VIA PATTERN BASED GRAPH VISUALIZATION. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

PDF (Dissertation Emilio Zegarra 2015)
Primary Text

Download (2MB)


High quality education in Science, Technology, Engineering and Math (STEM) majors expects not only the acquisition of comprehensive domain knowledge, but also the mastery of skills to solve open-ended and even ill-defined problems in real world. Problem-based Learning (PBL) is usually adopted to achieve such goals by encouraging students to learn by solving real-life problems. However, successful PBL requires sustained and in-depth involvement of faculty members, hence making PBL not scalable. Even though discussion forums and Q&A systems can help address the scalability problem of faculty involvement on large class sizes, it introduces new problems. First, as knowledge bases grow in size, the sheer size of the accumulated knowledge makes it harder to locate the desired information. Second, existing knowledge discovery techniques do not provide effective facilities for the capture and reuse of solutions to recurring problems.
To address these challenges, we developed MicroBrowser, an innovative and interactive Question & Answer (Q&A) system augmented with pattern-based expertise-sharing interfaces and 2D knowledge graph discussion visualization. MicroBrowser provides a set of pattern-based expertise-sharing interfaces to allow both learners and instructors to refine, reuse, and share knowledge. MicroBrowser also allows learners to browse and navigate important discussions based on topic similarity encoded by node proximity in a knowledge graph.
Results of empirical evaluations of our proposed solution show that ask difficulty improves with MicroBrowser when compared with a state-of-the-art Q&A system for knowledge discovery and reuse tasks. In addition, success rate for knowledge discovery tasks using keywords was higher with MicroBrowser. Moreover, we show that, students found the pattern-based expertise-sharing interface easy to use and were able to contribute new knowledge in the form of new knowledge connections and even recommend new design patterns.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Zegarra, Emilioezegarra@cs.pitt.eduEFZ2
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairChang, Shi-Kuochang@cs.pitt.eduSCHANG
Committee MemberWang,
Committee MemberLitman, Diane J.litman@cs.pitt.eduDLITMAN
Committee MemberSchunn, Christian D.schunn@pitt.eduSCHUNN
Committee MemberIriti, Jennifer E.iriti@pitt.eduIRITI
Date: 1 October 2015
Date Type: Publication
Defense Date: 10 July 2015
Approval Date: 1 October 2015
Submission Date: 24 July 2015
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 212
Institution: University of Pittsburgh
Schools and Programs: Dietrich School of Arts and Sciences > Computer Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: knowledge, patterns, visualization
Date Deposited: 01 Oct 2015 19:56
Last Modified: 19 Dec 2016 14:42


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item