Abstracts Computer Science

Intelligent Agents for On-line Learning

by Choonhapong Thaiupathump

This work offers a new paradigm for building intelligent software systems that facilitate on-line learning. The research investigated effects of adopting intelligent agent techniques to an on-line learning environment. KnowBots (or Knowledge Robots) are intelligent agents created specifically for this research. These KnowBots employed intelligent agent techniques to provide assistance to learners and facilitators who participated in a series of on-line workshops. The KnowBot architecture created was based on a study of repetitive tasks of human workshop facilitators. KnowBots automated and reduced the number of these routine tasks. The study specifically captured experimental results of using KnowBots in two sessions of the ALN on-line workshop, Getting Started Creating On-line Courses. Using two experimental groups, the effect of the use of KnowBots on workshop completion was examined as well as the effects of KnowBots on other factors such as facilitation time and learner satisfaction. The findings showed that intelligent agent technology holds promise for application to on-line learning and indicated that the use of KnowBots was positively associated with higher learner completion rates in the workshops. In addition, KnowBots implemented a learning-support tool that reminded learners about deadlines. The support KnowBots were found to be effective autonomous motivators. In sum, the results of this research suggest that the application of agent technology to on-line learning holds great promise.