Student Modeling for a Web-Based Learning Environment: A Data Mining Approach

Abstract

This ongoing research focuses on how data mining techniques, if incorporated into web learning environments, can enhance the overall qualities of learning. In a web-based learning environment, where both the tutors and learners are separated spatially and physically, student modeling is one of the biggest challenges. Traditional student modeling techniques are inapplicable in these systems when tutors are overwhelmed by the huge volumes of sequential data (Agrawal and Srikant 1995) generated as learners browse through the web pages. Web mining techniques, including clustering and association rules mining, could be applied to extract hidden and interesting knowledge to facilitate instructional planning and student diagnosis. Web mining in education is not new. It has been applied to mine aggregate paths for learners engaged in a distance education environment (Ha, Bae and Park 2000); to recommend relevant words to students based on text mining from their browsed documents (Ochi et al. 1998); to recommend e-articles for students based on key-word-driven text mining (Tang et al. 2000), and to analyze learners’ learning behaviors (Zaiane and Luo 2001). The research proposed here will go beyond usage mining to consider the content of the pages that have been visited. In an e-learning system, both learners’ browsing behaviors and course content are important to derive learners’ learning levels, intentions, goals, interests, or abilities. Incorporating course content can aid in an understanding of learners’ browsing habits. In particular, understanding the learners’ browsing behaviors can facilitate, say, the personalization of course contents delivered. Artificial intelligence in education (AIED) systems typically employ a knowledge base, a student model, and instructional plans. For a web-based AIED system, web mining becomes part of student modeling. Traditional usage data (Cooley 2000) keeps a lot of information that is not needed. But we do need the knowledge of content and complexity of each page. Finding and using such knowledge is tractable in our domain since we can annotate course web pages with metadata and the knowledge base, and instructional plan also give context for the properties of each page. The system can relate its mined knowledge of page contents and student navigation patterns to students’ level of understanding (Tang et al. 2001) to decide upon appropriate feedback to them.