Networked Collaboration Modules for Integrating Mathematics and Engineering Education Using Intelligent Agents

This CCLI Phase II project seeks to create and assess freely-available, intelligent agent-monitored, internet chat-based modules for integrating mathematics and engineering undergraduate education (Kumar & Rosé, 2011; Kumar et al., 2011; Ai et al., 2010; Kumar et al., 2010; Beuth et al., 2010). These modules help students relate mathematical concepts such as differentiation, integration and differential equations to their application in engineering. Further, monitored chat-based modules are developed as a unique, efficient outreach tool, allowing middle and high school students to make motivational links between mathematics and engineering, while learning what engineers do. These tasks are structured to be the basis for long-term transformational changes in how we teach engineering.

Two recent developments are exploited to realize this goal. They are: 1) At Carnegie Mellon, an earlier Phase I CCLI project has successfully demonstrated the integration of interactive dialogue technology with computer-based instruction in first year undergraduate and middle school outreach environments (Kumar et al., 2007; Rosé et al., 2006). Furthermore, it has been shown that the benefits of this technology can be enhanced if students work in on-line environments providing context-sensitive structuring to support team collaboration. 2) NSF-supported research at Wright State University and 19 other higher education institutions is demonstrating methods for successfully integrating mathematics and engineering education at the freshman level. The foundation of this effort is the development of a first year course combining mathematics and engineering applications in a way that motivates more extensive learning of both subjects in later courses.

The goal of this Phase II project is to use the agent-monitored dialogue technology from our Phase I project (Kumar & Rosé, 2009; Kumar & Rosé, 2011; Adamson & Rosé, 2012) as an alternative means for delivering many of the pedagogical goals of the Wright State approach, without offering a separate freshman-level course. As such, we see this as a low-barrier alternative delivery mechanism for universities not able or willing to commit to the larger curricular changes the Wright State approach suggests. This project involves a partnership between CMU Mechanical Engineering (ME), the CMU Human-Computer Interaction Institute (HCII), the CMU C-MITES Program, the University of California at Santa Barbara (UCSB) and Wright State University (WSU). ME and HCII students and faculty are collaborating to develop undergraduate-level dialogue-based projects that emphasize the use of mathematical tools and concepts in engineering design and analysis. The CMU C-MITES Program works with the PIs to integrate tutorial-led software experiences into their outreach program, with dialogues developed to instruct and inspire middle school students. UCSB incorporates modules developed at CMU into their own engineering undergraduate program, and provide feedback on their transferability. WSU helps guide the project with their extensive knowledge of what does and does not work in integrating mathematics and engineering instruction.

Selected Recent Publications

1. Adamson, D. & Rosé, C. P. (2012). Coordinating Multi-Dimensional Support in Conversational Agents, ITS 2012 Proceedings of the 11th International conference on Intelligent Tutoring Systems, Lecture Notes in Computer Science Volume 7315, Springer-Verlag, pp 346-351.
2. Kumar, R. & Rosé, C. P. (2011). Architecture for building Conversational Agents that support Collaborative Learning, IEEE Transactions on Learning Technologies, 4(1), pp 21-34
3. Kumar, R., Beuth, J., Rosé, C. P. (2011). Conversational Strategies that Support Idea Generation Productivity in Groups, in Proceedings of the 9th International Computer Supported Collaborative Learning Conference, Volume 1: Long Papers, pp 398-405.
4. Kumar, R. & Rosé, C. P. (2010). Engaging learning groups using Social Interaction Strategies, In Proceedings of the 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, short papers, pp 677-680
5. Ai, H., Kumar, R., Nguyen, D., Nagasunder, A., Rosé, C. P. (2010). Exploring the Effectiveness of Social Capabilities and Goal Alignment in Computer Supported Collaborative Learning, in Proceedings of Intelligent Tutoring Systems, Lecture Notes in Computer Science Volume 6095, pp 134-143.
6. Kumar, R., Ai, H., Beuth, J., Rosé, C. P. (2010). Socially-capable Conversational Tutors can be Effective in Collaborative Learning Situations, in Proceedings of Intelligent Tutoring Systems, Lecture Notes in Computer Science Volume 6095, pp 156-164.
7. Beuth, J., Rosé, C. P., Kumar, R. (2010). Software Egent-Monitored Tutorials Enabling Collaborative Learning in Computer-Aided Design and Analysis, in Proceedings of the ASME 2010 International Mechanical Engineering Congress & Exposition (IMECE2010), Vancouver, British Columbia, Canada.
8. Kumar, R. & Rosé, C. P. (2009). Building Conversational Agents with Basilica, Proceedings of NAACL HLT 2009: Demonstrations, pp 5–8, Boulder, Colorado, June 2009.
9. Kumar, R., Rosé, C. P., Wang, Y. C., Joshi, M., Robinson, A. (2007). Tutorial Dialogue as Adaptive Collaborative Learning Support, Proceedings of the 2007 conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work, Nominated for a Best Paper Award pp 383-390
10. Rosé, C. P., Kumar, R., Aleven, V., Robinson, A., Wu, C. (2006). CycleTalk: Data Driven Design of Support for Simulation Based Learning, International Journal of Artificial Intelligence in Education Special Issue on The Best of ITS ’04, 16, 195-223.