Web-Based Bayesian Intelligent Tutoring Systems
The rapid development of the World Wide Web offers an opportunity to apply a large variety of artificial intelligence technologies in various practical applications. In this chapter, we provide a review of our recent work on developing a Web-based intelli
- PDF / 1,478,045 Bytes
- 22 Pages / 430 x 660 pts Page_size
- 71 Downloads / 186 Views
Abstract. The rapid development of the World Wide Web offers an opportunity to apply a large variety of artificial intelligence technologies in various practical applications. In this chapter, we provide a review of our recent work on developing a Web-based intelligent tutoring system for computer programming. The decision making process conducted in our intelligent system is guided by Bayesian networks, which are a proven framework for uncertainty management in artificial intelligence based on probability theory. Whereas many tutoring systems are static HTML Web pages of a class textbook or lecture notes, our intelligent system can help a student navigate through the online course materials, recommend learning goals, and generate appropriate reading sequences.
10.1 Introduction Web-based education is currently an area of intense research and development. The benefits of Web-based education are clear: classroom independence, easy accessibility and greater flexibility [5]. Students control their own pace of study and do not depend on rigid classroom schedules. Thousands of Web-based courses and Web-based tutoring systems have been made available over the last five years [5, 63]. Many Web-based tutoring systems, however, are unable to satisfy the heterogeneous needs of users [5, 7]. These tutoring systems are static HTML Web pages, which act simply as copies of regular textbooks. This kind of tutoring system suffers from two major shortcomings, namely, it is neither interactive nor adaptive [5]. Many Web courses present the same learning materials to students with widely differing knowledge levels of the given subject. In fact, Brusilovsky and Maybury [6] explicitly state that an effective system must be robust enough to deal with various types of users. To resolve the traditional “one-size-fits-all” problem, it is necessary to develop systems with an ability to adapt their behavior to the goals, tasks, interests, and other features of individual users and groups of users. In this chapter, we provide a review of our recent work [9, 10, 11] on developing a Bayesian Intelligent Tutoring System, called BITS. BITS can be used on stand-alone computers or as a Web-based application that delivers knowledge through the Internet. BITS is based on Bayesian networks [48] - a formal framework for uncertainty management in artificial intelligence and supports student learning. We describe the architecture of BITS and examine the role of each component in the system. In particular, we discuss how to employ Bayesian networks as an inference engine to guide the students’ learning R. Nayak et al. (Eds.): Evolution of the Web in Artificial Intel. Environ., SCI 130, pp. 221–242, 2008. c springerlink.com Springer-Verlag Berlin Heidelberg 2008
222
C.J. Butz, S. Hua, and R.B. Maguire
processes. Moreover, we describe the features that allow BITS to be accessed via the Web. Beside Web-based tutoring systems, we also provide a comprehensive survey of related work involving Bayesian networks in various Web-based tasks. There are two fav
Data Loading...
