Application of Data-Mining Technology on E-Learning Material Recommendation

“Information overload” problem is even more emphasized with the growing amount of text data in electronic form and the availability of the information on the constantly growing World Wide Web (Mladenic et. al., 2003). When a user enters a keyword, such as “pencil” into a search engine, the result returned is often a long list of web pages, many of which are irrelevant, moved, or abandoned (Smith et. al., 2003). It is virtually impossible for any single user to filter out quality information under such overloading situation (Shih et. al., 2007). Designing appropriate tools for teaching and learning is a feasible approach to reduce the barriers teachers might encounter when adopting technology in their teaching (Marx et. al., 1998; Putnam & Borko, 2000). With potentially hundreds of attributes to review for a course, it is hard for the instructor to have a comprehensive view of the information embedded in the transcript (Dringus & Ellis, 2005). Computer-based systems have great potential for delivering learning material (Masiello, Ramberg, & Lonka, 2005), which frees teachers from handling mechanical matters so they can practice far more humanized pedagogical thinking. However, information comes from different sources embedded with diverse formats in the form of metadata, making it troublesome for the computerized programming to create professional materials. (Shih et. al., 2007).The major problems are: (1)Difficulty of learning resource sharing. Even if all E-earning systems follow the common standard, users still have to visit individual platforms to gain appropriate course materials contents. It is comparatively inconvenient. (2) High redundancy of learning material. Due to difficulty of resource-sharing, it is hard for teachers to figure out the redundancy of course materials and therefore results in the waste of resources, physically and virtually. Even worse, the consistency of course content is endangered which might eventually slow down the innovation momentum of course materials. (3) Deficiency of the course brief. It is hard to abstract course summary or brief automatically in efficient way. So, most courseware systems only list the course names or the unit titles. Information is insufficient for learners to judge quality of course content before they enroll certain courses. Application of Data-Mining Technology on E-Learning Material Recommendation 213