Year: 2015
Type: article
Abstract: Enabling the formative assessment of students while limiting demands on teachers’ time is a significant concern for technology mediated learning in small groups. Previous approaches have either required extensive time commitments on the part of teachers or relied on the development of special computational models of behavior. Oftentimes, these models overlook the way in which traces of student interaction in a learning system also constitute traces of human behavior, and, act only as “blunt instruments” relying only on the automated accounting of student activities. We employ activity theory to categorize traces of student behavior captured from a Virtual Math Teams (VMT) geometry class in an online, synchronous environment. From this, six semantically-grounded measures are generated for each student. Using these, a recently-developed clustering algorithm – spectral clustering – is coded to identify students who have similar behavior patterns. Structured in such a fashion, the theoretical and computational approach taken allows for an automated and meaningfully-grounded assessment of student performance, enabling teachers to offer concrete and personalized help in a timely format.
Authors: Wanli Xing, Sean Goggins
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W2300613051
