Towards Optimization of Macrocognitive Processes: Automating Analysis of the Emergence of Leadership in Ad Hoc Teams

The objective of the Ad Hoc Teams project is to facilitate emergence of shared leadership in ad hoc teams through context sensitive support to enable proactive decision making. What this means is optimization of group knowledge construction, leading to the formation of more effective plans in less time. We can only meet this objective if we facilitate getting the right information to the right people at the right time AND getting the right people to contribute their expertise at the right time. The key to enabling the basic research to understand how to design such support as well as the technology to provide the support in real time is a foundation in machine learning and language technologies, which underlie an infrastructure that speeds up the data to actionable knowledge loop. A key component of this effort is the establishment of a central repository for CDM data and analyses, the Combined Canonical CDM Corpus (C4), that will play a central role in the data to actionable knowledge loop, and will provide a valuable resource for the whole CDM community. Seven years of successful evaluation studies of the basic architecture for technology supported collaboration developed in our prior work provides a strong demonstration of its potential impact on task success for group knowledge construction and strategic planning tasks. Conversation technology offers interactive support for teams.

Selected Recent Publications

1. Rosé, C. P. & Borge, M. (in preparation). Measuring Engagement in Social Processes that Support Shared Cognition, Invited chapter in E. Salas & Fiore, S. (Eds.) Developing Multidisciplinary Measurement Approaches for Team Cognition Research, American Psychological Society.
2. Kumar, R. & Rosé, C. P. (in press). Triggering Effective Social Support for Online Groups. ACM Transactions on Interactive Intelligent Systems.
3. Howley, I., Mayfield, E., Rosé, C. P., & Strijbos, J. W. (in press). A Multivocal Process Analysis of Social Positioning in Study Group Interactions, in Suthers, D., Lund, K., Rosé, C. P., Teplovs, C., Law, N. (Eds.). Productive Multivocality in the Analysis of Group Interactions, edited volume, Springer.
4. Rosé, C. P. (in press). A Multivocal Analysis of the Emergence of Leadership in Chemistry Study Groups, in Suthers, D., Lund, K., Rosé, C. P., Teplovs, C., Law, N. (Eds.). Productive Multivocality in the Analysis of Group Interactions, edited volume, Springer.
5. Howley, I., Mayfield, E. & Rosé, C. P. (2013). Linguistic Analysis Methods for Studying Small Groups, in Cindy Hmelo-Silver, Angela O’Donnell, Carol Chan, & Clark Chin (Eds.) International Handbook of Collaborative Learning, Taylor and Francis, Inc.
6. Joshi, M., Dredze, M., Cohen, W. & Rosé, C. P. (2013). What’s in a Domain? Multi-Domain Learning for Multi-Attribute Data. Proceedings of the North American Chapter of the Association for Computational Linguistics
7. Joshi, M., Dredze, M., Cohen, W. & Rosé, C. P. (2012). Multi-Domain Learning: When Do Domains Matter, in Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012, July 12-14, 2012, Jeju Island, Korea, pp 1302-1312.
8. Jain, M., McDonogh, J., Gweon, G., Raj, B., Rosé, C. P. (2012). An Unsupervised Dynamic Bayesian Network Approach to Measuring Speech Style Accommodation, EACL 2012 Proceedings of the 13th Conference of the European Association for Computational Linguistics, Avingon, France, April 23-27, 2012, pp787-797.