Carolyn P. Rosé is an Associate Professor at the Language Technologies Institute and Human-Computer Interaction Institute at Carnegie Mellon University. Dr. Rosé is also an Executive Committee member of the Pittsburgh Science of Learning Center, Secretary/Treasurer and elected member of the Board of Directors of ISLS and involved in a number of additional learning-focused startups and projects. Dr. Rosé’s research spans the areas of Computer Supported Collaborative Learning, Automated Analysis of Collaborative Learning Discussion and Assessment of Collaborative Problem Solving, and has been funded by groups ranging from the National Science Foundation to DARPA. Dr. Rosé is also active in the fields of Computational Linguistics, Discourse Analytics, Tutorial Dialogue Agents, Discourse for Learning, Dialogic Instruction, Learning Sciences and more. Dr. Rosé holds a B.S. in Information and Computer Science from the University of California Irvine, and an M.S. in Computational Linguistics and a Ph.D. in Language and Information Technologies from Carnegie Mellon University.


Question: How did your educational trajectory (background) affect your current work?
Answer: I earned my PhD in Language and Information Technologies at Carnegie Mellon University in 1998, after which I did a Postdoc at the Learning Research and Development Center where I received training in the Learning Sciences and behavioral research methods. My current research program as an Associate Professor at the Language Technologies Institute and Human-Computer Interaction Institute at Carnegie Mellon University builds on this foundation by focusing on better understanding the social and pragmatic nature of conversation, and using this understanding to build computational systems that can improve the efficacy of conversation between people, and between people and computers. In order to pursue these goals, I invoke approaches from computational discourse analysis and text mining, conversational agents, and computer supported collaborative learning.

My approach is always to start with investigating how conversation works and formalizing this understanding in models that are precise enough to be reproducible and that demonstrate explanatory power in connection with outcomes that have real world value. The next step is to adapt, extend, and apply machine learning and text mining technologies in ways that leverage that deep understanding in order to build computational models that are capable of automatically applying these constructs to naturally occurring language interactions. Finally, with the technology to automatically monitor naturalistic language communication in place, the next stage is to build interventions that lead to real world benefits.

Question: What professional experiences have been most formative to your current work?
Answer: One of the most exciting recent collaborations I have been involved in in recent years has been in the context of the Pittsburgh Science of Learning Center where I co-lead the Social and Communicative Factors of Learning research thrust with Lauren Resnick from the Learning Research and Development Center. In the context of this collaboration, I have been investigating both the role of facilitation behaviors valued within the Classroom Discourse literature in a collaborative learning context as well as the role online collaborative activities can play in preparing high school students for whole class teacher led discussions as part of a multi-year professional development program. A series of studies we have run evaluating intelligent conversational agents employing teacher facilitation practices from the Classroom Discourse literature called Academically Productive Talk (APT) moves demonstrates their significant positive impact on learning and interaction during collaborative learning. Furthermore, using technology supported analysis of classroom discussions collected over the two year program, we have determined that preparing students prior to teacher led discussions by means of conversational agent facilitated online collaborative learning activities has an enabling effect on teacher uptake of productive classroom facilitation practices.

Question: How do you hope your work will change the learning landscape?
Answer: With the recent press given to online education and increasing enrollment in massively open online courses, the need for scaling up quality computer-mediated educational experiences has never been so urgent. Current offerings provide excellent materials including video lectures, exercises, and some forms of discussion opportunities. The biggest limitations are related to the human side of effective educational experiences including personal contact with instructors and the cohort experience. These concerns prompt my research on interventions that improve the instructional value of online collaborative learning experiences.

Question: What broad trends do you think will have the most impact on learning in the years ahead?
Answer: As I continue to work towards supporting collaborative interactions within thriving online learning communities, I am becoming aware of the need to understand how local interactions within pairs or small groups may lead to emergent behavior at the community level, which may then exert downward causality on behavior at the individual and small group level. A new wave of dynamic support technologies will more fully take these emergent properties of online communities properly into account. The key to making progress on this agenda is to bring together deep insights about human interaction from the fields of Psychology, Sociolinguistics, and Discourse Analysis with techniques from Machine Learning and Statistics.

Question: What are you currently working on & what is your next big project?
Answer: My group’s research has birthed and substantially contributed to the growth of two thriving inter-related areas of research: namely, Automated Analysis of Collaborative Learning Processes and Dynamic Support for Collaborative Learning, where intelligent conversational agents are used to support collaborative learning in a context sensitive way. At least a decade of research, including my own, shows that students can benefit from their interactions in learning groups when automated support is provided, especially interactive and context sensitive support. 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 scripted 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 "listen in" on student conversations in search of important events that present opportunities for discouraging dysfunctional behavior or encouraging positive behavior using automated analysis of collaborative learning processes. My group 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. Building on these successes, I am now engaged in a partnership with Lauren Resnick and the Institute for Learning to investigate how to leverage these findings in the context of large-scale dissemination of APT professional development through Coursera.

Image: Courtesy Carolyn P. Rosé