Intelligent pedagogical agents for personalizing learning objects in educational environments

• Main Author: Ashoori, Maryam
• Other Authors: Miao Chun Yan
• Format: Theses and Dissertations
• Language: English
• Published: 2008
• Subjects: DRNTU::Engineering::Computer science and engineering::Computer applications::Social and behavioral sciences; DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: https://hdl.handle.net/10356/13582
• Institution: Nanyang Technological University

A key issue in pedagogy is individualization, i.e., adapting the teaching to the needs of various learners. In many cases, however, current e-learning systems have so far focused most on porting existing courses with traditional teaching methods onto the web/grid environments, just making non-individualized teaching even more widely available. The majority of current e-learning systems treat every user equally with out any fine-tuning at the learning objects. This research proposes a combination of pedagogical achievements and intelligent agents toward developing such personalized learning spaces and improving the effectiveness of learning achievements through an interactive learning environment. The presented intelligent technology has potential regarding the creation of more intelligent, personalized, adaptive and interactive e-learning applications, providing individualization and therefore enhancing the effects of learning. The proposed approach, however, is not limited to e-learning systems. This idea can be applied to a wide variety of application domains where personalizing the content could improve the performance. This Research is part of the project of "Agent Augmented Virtual Environment" which explores agent augmented immersive virtual and mixed world to develop and as- sess immersive/situated learning environments. It collaborates with the National Science Foundation funded project, "Multi-User virtual Environments (MUVEs)" at Harvard. The whole project is to study (1) immersive/situated learning and (2) the ways in which agent augmented virtual environments may aid the transfer of learning from classroom contexts into real world settings. The research team of MUVE at Harvard developed the "River City" curriculum, teams of middle school students are asked to collaboratively solve a simulated 19th century city's problems with illness, through interaction with each others, avatars, digital artifacts, tacit clues, and computer-based agents acting as mentors and colleagues in a virtual community of practice. The research team at NTU focuses on software agents, multi-agent system, and agent augmented virtual and mixed environment. The team targets to infuse agent technology into various environments and application domains e.g. agent augmented virtual reality and mixed reality etc. Taking an interdisciplinary approach, the NTU team and Harvard team collaborate with each other to explore agent mediated situated learning environment and agent mediated learning community. Precisely speaking, this approach is toward an effective negotiation protocol among self-interested mentors of an agent augmented virtual environment, Virtual Singapura, for personalizing learning process and thereafter maximizing learning achievements. The synthetic characters in this environment are augmented with advanced agent technologies in order to investigate contextual, situational, social, and emotional dimensions of virtual experiences for learning. This research is to develop an e ective individualization in order to providing highly accurate personalized guides according to the student's background. Agent society is equipped by situation and location awareness which let the agents track the students during the whole process of learning. Specifically, proposed approach is an inspiration of the main concept of pricing in market-based systems combined with the belief accumulation of Dempster-Shafer theory to develop a rational society of self motivated agents who provide personalized helps for learners over the learning environment. Assessments illustrated that students who use this multiuser virtual environment can construct deep understandings of scientific concepts and develop science inquiry skills, as well as the ability to transfer or apply their new knowledge and skills to new situations. In between, personalization has performed an effective role which has highly improved the learner performance in addition to make the students find agents as believable as virtual mentors.