Overview
The Teachable Agents Project combines research from computer science, psychology, and education to develop computer-based learning environments. These environments utilize animated pedagogical agents to facilitate science learning and the development of self-regulated learning skills.
The use of animated agents allows us to extend the cognitive scaffolding provided by various computer tools and representations (e.g., searchable text, simulations, concept maps, etc.) by embedding them in productive and motivating social-constructive interactions (e.g., peer teaching, collaboration, and assessment).
Recent work has focused on our Betty's Brain system in which middle school students learn by teaching an agent about a river ecosystem. Students study online text materials to acquire background knowledge, teach this information to Betty, and then assess her understanding using questions and quizzes.
Our data collection also includes extensive logging of students' interactions with the system and agents. We can use a variety of data mining techniques to use these data to make inferences about students' prevailing learning strategies. Several projects have explored the use of hidden Markov models as a method of identifying such patterns.
On this site you will find information about our past and current research, publications, and team members. A version of the Betty's Brain software can also be downloaded!