Student Behavioral Model Based Prefetching in Online Tutoring System

摘要: Web-based tutoring systems provide important advantages as a supplement to traditional classroom instruction. MANIC (Multimedia Asynchronous Networked Individualized Courseware) is an interactive multimedia WWW-based tutoring system that was originally developed in 1997 and was used by more than 200 users during the Spring 1997 semester to listen to, and view, the stored audio lectures and lecture notes for a full-semester seniorlevel Networking course at the University of Massachusetts [9]. Previous work has been done to analyze and improve the performance of MANIC from both system’s and users’ perspective [9] providing empirical and analytical characterizations of observed user behavior in MANIC. The work in [9] focused on studying the sessionlevel behavior (eg, the length of individual sessions) and interactive user behavior (eg, the time between starting/stopping/pausing the audio within a session).[14] built and analyze a student model for MANIC, and determining the level of difficulty and the learning style preferences of a student by using a Naive Bayes Classifier.Differing from previous work on MANIC, we will use a Hidden Markov Model (HMM) approach to capture students’ behavior individually and study the use of HMMs to implement prediction algorithms for prefetching lecture notes. Some past research has been done to predict HTTP requests [13] and predict requests to web servers [2], but they were all from the server’s (system’s) point of view. Our focus is on characterizing the behavior of individual users. Work has also been done to construct a user model for tutoring systems using machine learning techniques …