Free on-line learning promises to transform the educational landscape of the United States through a significant broadening of supplemental educational opportunities for low income and minority students who do not have access to high quality private tutoring to supplement their in school education. The proposed solution is to develop a technological augmentation to available human support in a lightly staffed Virtual Math Teams (VMT) environment as well as deploying conversational agents that are triggered by automatically detected conversational events and that have the ability to elicit valuable collaborative behavior such as reflection, help seeking, and help provision. This project brings together expertise in technological development and careful experimentation both in the lab and in the classroom, a track record for large scale deployment of educational materials, and a solid foundation in significant student learning results in collaborative environments. The project builds on results from a pilot project in which the team has built VMT-Basilica, which is a technical infrastructure for supporting collaborative problem solving, as well as having conducted pilot studies with it in an on-line setting with promising results. The VMTs use the infrastructure provided by the Math Forum. This project also contributes to the general development of intelligent agents to aid collaboration in a wide variety of settings where collaboration support is needed. By bringing together research in education environments and in computer based intelligent agents, this project is potentially transformative in both computer science and mathematics education.
The project has the potential to bring mathematics to a national community since the development of these agents will substantially reduce the amount of time a human must monitor VMT collaborations. VMTs operate primarily out of the classroom and act as supplemental work for students learning mathematics. In addition, since the collaboration support provided by these agents is not specific to mathematics problem solving, agent supported collaboration could be expanded to any field where collaboration needs to be supported - from education to business to the military.
This project’s research has produced innovative support for group learning and has evaluated its success in numerous classroom studies over the four years of project funding. Until recently, the state-of-the-art in computer supported collaborative learning has consisted of static forms of support, such as structured interfaces, prompts, and assignment of students to roles. This earlier work, referred to as scripted collaboration, has been a major focus of the field of Computer Supported Collaborative Learning in the past decade, and despite its limitations, has produced numerous demonstrations of its effectiveness in improving collaborative learning. In contrast, dynamic forms of collaboration support use technology to monitor group discussions in collaborative learning exercises in search of important events that present opportunities for discouraging dysfunctional behavior or encouraging positive behavior using automated analysis of collaborative learning processes. The research team is widely recognized as playing a major role in enabling this paradigm shift, especially as a result of demonstrations that dynamic script based support leads to improvements in learning over otherwise equivalent static forms of support. Its value has been recognized in award and award nominations at academic conferences. In particular, the results of this research demonstrated that students can benefit from their interactions in learning groups when automated support is provided, especially interactive and context sensitive support such as developed under this grant. In one study, students in collaborative pairs with support from a dynamic support agent learned one and a quarter letter grades more than students who worked individually without the support. The team collaborated with Lauren Resnick at the Learning Research and Development Center to develop a specific style of dynamic support agents that base their behavior on productive teacher facilitation practices called accountable talk. Results from four studies demonstrate the positive impact of the accountable talk agents on student learning. As a demonstration of the impact of the dynamic support in the face-to-face realm of the classroom, the project team has been investigating the role online collaborative activities can play in preparing high school students for whole class teacher led discussions as part of a two year teacher professional development program. Using technology supported analysis of classroom discussions collected over the two year program, we have determined that preparing students prior to teacher lead discussions by means of conversational agent facilitated online collaborative learning activities also has a positive effect on the interaction between the teacher and the students in the classes during whole class teacher led discussions that follow the online exercises. Building on these successes, the team is moving on from this funded project to engage with Lauren Resnick and the Institute for Learning to investigate how to leverage these findings in the context of large scale dissemination of accountable talk professional development through Coursera. A current offering of instruction on accountable talk through Coursera has over 35,000 students enrolled for participation starting in September of 2013. In the near term, an important focus of this active collaboration surrounding this Coursera course is using automated analysis of threaded discussions with 35,000 participants to enable human instructors to support that interaction.
