Principal Investigator: Kurt VanLehn
CoPrincipal Investigator(s):
Organization: Arizona State University

Abstract:
The Future of Work at the Human-Technology Frontier (FW-HTF) is one of 10 new Big Ideas for Future Investment announced by NSF. The FW-HTF cross-directorate program aims to respond to the challenges and opportunities of the changing landscape of jobs and work by supporting convergent research. This award fulfills part of that aim. Expert teachers effectively orchestrate the complex flow of ideas and products in the classroom through individual, small group, and whole class activities. In supporting the future work of teachers, this project will facilitate the classroom orchestration process through the development of an intelligent teaching assistant, implemented as a tablet-based dashboard. This will allow the teacher to delegate cognitively-demanding orchestration tasks related to classroom activities to the intelligent assistant, enabling him/her to focus on other tasks to support student learning. Building on an existing shared-document system for middle school mathematics teachers, the proposed system will facilitate teachers in monitoring student work, assessing it, and making conclusions (e.g., indicating student progress, errors, and misconceptions) while allowing them to circulate among students who are working individually or in small groups. Ultimately, the system will behave like an automated teaching assistant and allow teachers to be more effective and increase their job satisfaction by allowing them to concentrate on assisting learners who most need help.

Building on the team’s Formative Assessment with Computational Technologies (FACT) system, the development of an intelligent teaching assistant will enhance teachers’ awareness of what is going on in the classroom and facilitate the cognitively-intensive tasks of orchestrating classroom activities. In the first six-month phase, the project will employ a knowledge engineering process to uncover the tacit knowledge teachers use for decision-making in managing the flow of classroom activities. In the second phase, over two and one-half years, a series of ten comprehensive trials will be conducted to iteratively develop the cognitive policies of the system through data collection and optimizing the flow of work and ideas, carefully considering teacher input. This knowledge will be encoded in a rule-based Artificial Intelligence where the intelligent teaching assistant can perform some of the decision-making. Authorized by the teacher, it will send messages directly to students in specific situations – some will be feedback, some will be hints, some will be requests to visit other students and some will just be to redirect attention to get back on task. The automated teaching assistant will also prioritize tasks for the teacher; e.g., which students to visit in the classroom. As part of this process, new sensors will be added to FACT that will monitor the teacher’s speech and location. The potential broader impact includes facilitating teachers in conducting more pedagogically complex and effective lessons and increasing teacher job satisfaction while improving student learning.

This award reflects NSF’s statutory mission and has been deemed worthy of support through evaluation using the Foundation’s intellectual merit and broader impacts review criteria.