Facilitating Peer Learning and Knowledge Sharing in STEM Courses via Pattern Based Graph Visualization

Abstract

Abstract-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. Problem-based Learning (PBL) is usually adopted to achieve such goals. However, PBL requires sustained and indepth faculty involvement, hence making PBL not scalable. Also, existing knowledge discovery techniques do not facilitate the capture and reuse of solutions to recurring problems. To address these challenges, we present MicroBrowser, an interactive Q&A system augmented with 2D discussion visualizations and pattern based expertise sharing interfaces. MicroBrowser allows learners to browse and navigate important discussions in PBL based on topic similarity encoded by node proximity in a knowledge graph. MicroBrowser also provides a set of pattern based expertise sharing interfaces to allow both learners and instructors to highlight, share and reuse major findings in PBL. Through a 32-subject study, we found MicroBrowser to be effective at facilitating knowledge discovery. Moreover, students understood and were able to use design patterns to complete open ended tasks.