Dynamic Support for Virtual Math Teams

Principal Investigator: 
Project Overview
Background & Purpose: 

The proposed research attempts to understand how to structure interactions among peer learners in online education environments. It seeks to enhance effective participation and learning in the Virtual Math Teams (VMT) online math service, housed in the Math Forum, a major NSF-funded initiative that specifically targets inner-city, low-income minority students. This will be accomplished by designing, developing, testing, refining and deploying automated interventions to support significantly less expensive but nevertheless highly effective group facilitation. The key research goal is to experimentally learn broadly applicable principles for supporting effective collaborative problem solving by eliciting behavior that is productive for student learning in diverse groups.


Data will be collected initially from schools that the PIs are in close collaboration with and will expand to other schools that access the Math Forum.

Research Design: 

This project has a comparative research design and will generate evidence that is descriptive [design research], associative/ correlational [process analyses of conversational data, and causal [experimental]. Original data are being collected using assessments of learning, observation [web logs], and survey research [online questionnaires and focus groups]. Measures or instruments include a variety of content oriented tests and questionnaires that measure motivational constructs as well as perceptions of the collaboration and the computer environment.

Computer agents that support collaborative learning are being compared to alternative versions of the support agents. A major focus of our data analysis is process analyses of the collaborative discussions that occur within the Virtual Math Teams environment. Within the project, the data will be analyzed in three primary ways: (i) through manual qualitative conversation analysis, (ii) through leading-edge techniques of natural language processing and (iii) through mixed methods of qualitative and quantitative analysis, data mining, cluster analysis, statistical analysis and network analysis.


In an earlier pilot project we were able to integrate a current prototype of the proposed intervention with the Virtual Math Teams environment. We have run a series of successful research studies in classroom contexts with a variety of versions of the support intervention that have yielded interesting findings. Analysis of recent studies is in progress.

Publications & Presentations: 

Stahl, Gerry (2009). Studying Virtual Math Teams, Computer Supported Collaborative Learning Series, Vol. 11, Springer. HTTP://WWW.SPRINGER.COM/EDUCATION/LEARNING+&+INSTRUCTION/BOOK/978-1-4419-0227-6.

Other Products: 

The goal of the project is to produce interventions that improve the effectiveness of the Virtual Math Teams environment in ways that achieve maximal cognitive and social benefits for on-line learners. Expensive instructors and content providers will continue to develop instructional materials and act as moderators to the extent that resources allow. Their resources can be stretched by means of reporting technology that quickly and effectively assists them in identifying the teams that are in most need of their involvement. Fellow students will support each other in dealing with their struggles with the materials. Inexpensive software agents will aid human facilitators in matching students who can help each other as well as in offering help to structure their collaborative learning conversations to make them more effective.