Design and Implementation of the Adaptive Teachable Agent

Abstract

Traditionally intelligent tutoring system (ITS) uses expert model to deliver knowledge and train skills to users. According to the theories of leaning, learning by teaching method is more efficient for enhancing motivation to learn and cognitive ability than learning by listening or learning by reading. For the purpose of developing an intelligent agent to enhance the motivation to learn, the new type of teachable agent were designed and implemented, in which the user plays a role of a tutor by teaching the agent. In addition, we provide adaptive user interface where each user plays his/her own scenario according to level of interests and motivation. We design the program to teach the agent about ‘rock cycle’. The program consists of four modules: teach module, Q&A module, test module, and network module. In teach module, the user teaches the agent and the agent’s knowledge is structured and organized. In Q&A module, the user answer the question through an interactive window. In network module, the database server gathers log data of users to measure users’ interest and motivation about TA. It is expected that providing the user with the active role of teaching the agent enhance the motivation to learn and the positive attitude toward the subject matter as well as cognition.