Persuasive teachable agent for intergenerational learning

• Main Author: Lim, Su Fang
• Other Authors: Miao Chun Yan
• Format: Theses and Dissertations
• Language: English
• Published: 2016
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/69093
• Institution: Nanyang Technological University

Teachable agents are artificial intelligent computer agents designed around the pedagogical concept that students learn better when they teach others. During the tutoring process with a teachable agent, the students take on the role of the tutor to teach a teachable agent tutee. Students involved in this teaching process have been observed to gain a deeper understanding of the subject matter. Teachable agents are commonly used in the learning of science and mathematics where students are able to learn complex concepts and deep reasoning when they teach the teachable agent using graphical representations such as concept maps. Literature review on teachable agents have shown that many current teachable agents lack the ability to proactively interact with the students, an important feature required to keep students engaged in learning tasks. As a result, students deviate from the teaching process, and are unable to benefit fully from learning with the teachable agent. In addition, most applications of teachable agents are restricted to the learning of academic subjects such as mathematics and science. As the global population is rapidly and resulted in increased interest in expanding the applications of teachable agents to utilize it as a tool to encourage intergenerational bonding as well as to benefit a wider group of users. In this thesis, the Persuasive Teachable Agent (PTA) is proposed, a teachable agent based on the theoretical framework of persuasion, computational and goal-oriented agent modelling. Firstly, our proposition is that persuasion theory, which attempts to influence behaviour and attitude change in the users allow the PTA to resolve interaction issues in existing TA by keeping users interested the process of teaching the agent. Secondly, we explore how the application of the PTA can be expanded outside the area of academic learning. In addition, we suggest that the PTA can be used to encourage intergenerational learning among users from different age groups. Therefore the PTA, an autonomous agent capable of encouraging attitude and behavioural change in humans, can offer a more meaningful and engaging learning experiences for users from different age groups. This research finds that persuasive feedback actions generated by the PTA provide significant influence on user’s decision to participate in intergenerational learning. The PTA plays a crucial role in the development of future persuasive technologies in artificial intelligent agents.