PIs: Jonathan Gratch, Peter Kim
University of Southern California
Award Details

This project advances the use of technology to improve worker communication and interpersonal skills. The project pursues a near-term vision that students and workers will soon be able to augment their interpersonal skills by receiving conversational practice and personalized tutorial feedback with automated teaching agents. By practicing effective strategies for handling common interpersonal challenges, such as challenges involving communication, working in teams, resolving conflicts, negotiation, or dealing with bias in the workplace, trainees will be able to enhance their employability, their on-the-job effectiveness, and their career opportunities. In particular, the project directly supports the education and full participation of women and underrepresented minorities in science, technology, engineering, and mathematics (STEM) by addressing identified obstacles to their advancement in STEM careers. Given the broad importance of interpersonal skills development, the project’s results are expected to have wide-ranging impact extending beyond its core research disciplines to include also law and political science as well as practical impact for applications such as job skills training and human-machine teaming.

This project advances the application of technology to interpersonal skills training by addressing several fundamental scientific and technical challenges in understanding their effectiveness and achieving broad deployment of these systems. It improves the ecological validity of previous menu-based training methods by using state-of-the-art spoken dialogue system technology to provide conversation-based training that enhances the realism of experiential learning. It addresses the high development costs of applying spoken dialogue system technology to interpersonal skills training by developing new techniques that reduce the costs in labor and knowledge required to teach specific learning objectives. Finally, the project designs and evaluates innovative methods that automated systems can use to provide individualized assessment and feedback to trainees. The objective of the project is to demonstrate the potential of automated, intelligent conversational agents to enhance the experiential learning of interpersonal skills, and enhance the science behind the use of automated tutors for teaching complex communicative skills. The project plan includes the design and implementation of a conversational agent, development of new approaches to automated assessment and feedback, data collection, and empirical validation of the training benefits of the approach. An expected outcome is an improved understanding of how technology can be effectively applied to a range of training needs in the areas of communication and interpersonal skills.