Group Cognition: Learning in Engineering Project Teams

Funded by: the National Science Foundation
PIs: Susan Finger, Daniel P. Siewiorek, Asim Smailagic, and Carolyn Rosé

Ideally, in engineering project courses, students co-construct the knowledge necessary to realize their designs through the processes of proposing, counter-proposing, questioning, arguing, agreeing, and dissenting. Although some of the work is done individually, a major portion is accomplished through group interactions, in which a group creates a shared understanding of the design. Each student learns the technical content necessary to realize his or her part of the final design, gains a deeper understanding of the other disciplines involved, and gains professional skills in communication, team work, and project planning. Computer-based collaboration tools, such as wikis and chat rooms, can make the collaboration process visible to instructors; however, instructors lack practical, analytical tools with which to monitor and evaluate the quality of the collaboration.

The long-term goal of our research is to develop technology for engineering project course instructors to aid them in assessing students' technical progress and in assessing group progress. We are developing tools to provide indicators of the project groups’ performance based on data that can be collected unobtrusively from groups as they work outside of the instructors' view. The project makes use of two sources of data. The first is a large corpus of data, collected from student design teams over four years, which includes both the on-line conversations and the documents created by the teams. This corpus is being used to develop design webs that are generated automatically from the data as it is captured. The design webs enable students and instructors to see both how ideas develop and how different team members contribute. The second source is speech recordings of group interactions. This includes one semester’s worth of recordings of team interactions from one of the semesters of a design course from the first corpus. These recordings are paired with assessments from direct observers of those meetings as well as the instructors assessment of team functioning from in class discussions and instructor-team meetings.

Our hypothesis is that instructors will be able to intervene in a more timely manner than they are currently able if we can provide them with greater insight into the inner workings of teams.

Following a user-centered design approach, we posed three research questions:
  1. What can be inferred about inter-group collaboration by monitoring student posts and participation in both online discussions and in person meetings where the instructor is not present?
  2. What can instructors learn about group performance from linguistic indicators that can be extracted from group communication?
  3. Can tracking changes in language usage over time, such introduction of new vocabulary or shifts in language style, reveal insights into design team collaboration?

Selected Recent Publications

  1. Gweon, G., Jain, M., Mc Donough, J., Raj, B., Rosé, C. P. (in press). Measuring Prevalence of Other-Oriented Transactive Contributions Using an Automated Measure of Speech Style Accommodation, International Journal of Computer Supported Collaborative Learning
  2. Habte, B., Finger, S., Rosé, C. P. (2013). E-Learning in Engineering through Videoconferencing: The case of Addis Ababa Institute of Technology, International Journal of Engineering Pedagogy (iJEP) 3(2).
  3. Gweon, G., Jain, M., McDonogh, J., Raj, B., Rosé, C. P. (2012). Predicting Idea Co-Construction in Speech Data using Insights from Sociolinguistics, in Proceedings of the International Conference of the Learning Sciences, Sydney, Australia.
  4. Gweon, G., Jeon, S., Lee, J., Rosé, C. P. (2011). Diagnosing Problems in Student Project Groups, in Puntambekar, S., Erkens, G., Hmelo-Silver, C. (Eds.) Analyzing Collaborative Interactions in CSCL: Methods, Approaches and Issues, Springer.
  5. Gweon, G., Agarwal, P., Udani, M., Raj., B., Rosé, C. P.(2011). The Automatic Assessmnet of Knowledge Integration Processes in Project Teams, in Proceedings of the 9th International Computer Supported Collaborative Learning Conference, Volume 1: Long Papers, pp 462-469 Best Student Paper Award
  6. Oberoi, S., Nguyen, D., Gweon, G., Finger, S., & Rosé, C. P. (2010). DesignWebs: A Tool for Automatic Construction of Interactive Conceptual Maps from Document Collections, in Proceedings of Intelligent Tutoring Systems, Lecture Notes in Computer Science Volume 6095, pp 387-389.
  7. Oberoi, S. V., Nguyen, D., Finger, S. and Rosé, C. P. (2010) Automatic extraction of Conceptual maps from design team documents, Proceedings of the International Design and Design Education (DEC), Montreal, Canada, August 15-18, 2010.
  8. Gweon, G., Kumar., R., Rosé, C. P. (2009). GRASP: The Group Learning Assessment Platform, Proceedings of the 9th international conference on Computer supported collaborative learning - Volume 2: Community Events Proceedings, pp 186-188.
  9. Gweon, G., Kumar, R., Rosé, C. P. (2009). Towards Automatic Assessment for Project Based Learning Groups, Proceedings of the 2009 conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modeling, pp 349-356.
  10. Rosé, C. P., Gweon, G., Arguello, J., Finger, S., Smailagic, A., Siewiorek, D. (2007). Towards an Interactive Assessment Framework for Engineering Design Learning, Proceedings of ASME 2007 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, pp 45-54.