Carolyn Penstein Rosé

Statement of Career Goals

My research program is focused 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. I ground my research in the fields of language technologies and human-computer interaction, and I am fortunate to work closely with students and post-docs from the Language Technologies Institute and the Human-Computer Interaction Institute, as well as to direct a lab of my own, called TELEDIA.

The specific goals of my current research are to develop technology capable of shaping conversation and supporting effective participation in conversation to achieve a positive impact on human learning, growth, and wellbeing. My conviction is that in order for technology to be maximally successful in this mission, the technology must first be capable of processing, generating, and engaging in conversation. Second, its behavior should be designed with a deep understanding of the mechanics of what makes conversation work in different settings as well as an understanding of what properties of conversation add to or detract from its positive impact on important outcomes of conversation. Finally, its design should be based on knowledge of what external stimuli manipulate these properties of conversation and in what ways.

My aim is to see my research make an impact in the world. To this end I am involved in efforts that have a clear path towards impacting individuals and communities around the world and transforming how they benefit from participation in computer-mediated interactions, including partnerships with The Math Forum, a major university based math service reaching millions of students each year, and dissemination through Worth Publishing.s Psychology Portal, which is packaged with our country.s most popular undergraduate psychology textbook. In order to ensure the real world impact of my work, I choose application areas with concrete benefits. The current application of my work falls within the three areas of education, disaster relief, and health and wellbeing.

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 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, my ultimate goal is to build interventions that lead to real world benefits.

This approach leads to three aspects to each project:

• Basic research in discourse analysis in order to identify conversational constructs that predict important group outcomes such as learning, knowledge transfer, relationship formation, impression management, motivation and decision making.
• Basic research on text classification technology for automated analysis of conversational constructs identified under (1) as well as tools to enable other researchers to do the same in their own work.
• Basic research on summarization and conversational agent technology that eases development of interventions triggered by automatic analyses from (2) that either enable human facilitators to offer support, directly provide feedback to groups, or behave in such a way as to influence group participation in positive ways.

In an effort to arrive at generalizable models, I am pursuing this research program in multiple parallel contexts that provide opportunities to investigate how both the manifestation of the conversational constructs as well as their effects on outcomes are nuanced through mediating contextual variables. Thus, I am conducting research in ten currently funded projects, each of which provides opportunities for pursuing these three types of research in one of my three primary application areas. Those projects are

• Education at the middle school, high school, and college level
  • Theories and Models of Group Cognition (ONR)
  • Investigating the Social and Communicative Factors in Learning (NSF)
  • ADEPT: Assessing Design Engineering Project Classes with Multi-Disciplinary Teams (NSF)
  • Group Cognition: Learning in Engineering Project Teams (NSF)
  • Agent-Monitored Tutorials to Enable On-Line Collaborative Learning in Computer-Aided Design and Analysis (NSF)
  • Networked Collaboration Modules for Integrating Mathematics and Engineering Education Using Intelligent Agents (NSF)
  • Dynamic Support for Virtual Math Teams (NSF)
• Emergency response
  • Towards Optimization of Macrocognitive Processes: Automating Analysis of the Emergence of Leadership in Ad Hoc Teams (ONR)
• Health and Wellbeing
  • Conversational Dynamics in Online Support Groups (NSF)
  • Dynamic Support for Computer-Mediated Intercultural Communication (NSF)