Print this pageWeb Mining in Education: Overview
The Web nowadays is a firmly established (virtual) reality that offers unprecedented opportunities to education. Many modes of delivery of online learning exist (e.g. edu-cational software, virtual courses, blended learning, electronic books), all providing accessibility to learning materials, facilitating communication among learners and tu-tors/peers, and possibly helping to improve the learning and teaching process. While using an online learning environment, learners leave continuous hidden traces of their activity in the form of log file records, which document every action taken by three parameters: what was the action taken, who took it and when. The primary objective of the proposed research is to develop and apply Web mining techniques that use these log files, in order to portray the characteristics of the learner's learning processes in online environments.
Web mining is a research area consisting of techniques and methods that automatically discover and extract information from Web log files. The term Web mining (Web data mining), was first mentioned by Etzioni (1996), who suggested that traditional data mining techniques - techniques for finding patterns submerged in huge databases - can be applied to Web-based information. Web mining has been massively used in e-commerce (e.g. in Amazon.com, where the customer's history is used for personalization and for encouraging further purchase), and is an emerging methodology in education research, assisting instructors and developers in improving learning environments and supporting decision-making of policymakers (Cohen & Nachmias, 2006).
Traditionally, Web mining techniques are sorted into three categories, by the type of information mined:
- Usage analysis aims to describe the usage of the system, in terms of three parameters in the log files: who used the system (e.g., IP address, username), what did she or he do (i.e. which page exactly did she or he visit) and when did she or he do it (i.e. date and time). This is the method to be used in the proposed research.
- Content analysis analyzes the system's content, e.g. Website texts, asynchronous discussion board messages, synchronous chat discussions.
- Structure analysis is used to characterize the interconnections among the various system components.
The first detailed model for applying usage mining as a research methodology was suggested by Cooley, Mobasher, and Srivastava (1997), and later a few other similar models were published, the most comprehensive of which is by Kosala & Blockeel (2000). In education, the need for such methods appeared as early as the appearance of the Web, and a detailed research framework (particularly referring to usage analysis) was published later by Pahl (2004) and Zaiane (2001), although earlier research already discussed the potential of analyzing online courses using this method (Rafaeli & Ravid, 1997). Unlike the use of Web mining in e-commerce - the target of which is to transform the surfer into a buyer - the same techniques in the context of e-learning aim to transform the learner into a more efficient learner. In addition, usage analysis of e-learning is totally different from usage mining of e-commerce, since the learning process is far more complicated than the shopping process, and its cognitive aspects are much more difficult to track by means of log files.
References
Cohen, A., & Nachmias, R. (2006). A quantitative cost effectiveness model for Web-supported academic instruction. The Internet and Higher Education, 9(2), 81-90.
Etzioni, O. (1996). The World Wide Web: quagmire or gold mine? Communications of ACM, 39(11), 65-68.
Kosala, R., & Blockeel, H. (2000). Web mining research: A survey. SIGKDD Explorations, 2(1), 1-15.
Mobasher, B., Dai, H., Luo, T., Sun, Y., & Zhu, J. (2000). Integrating Web usage and content mining for more effective personalization. Paper presented at the 1st International Conference on Electronic Commerce and Web Technologies (EC-Web'2000), London, UK.
Pahl, C. (2004). Data mining technology for the evaluation of learning content interaction. International journal of E-Learning, 3(4), 47-55.
Rafaeli, S., & Ravid, G. (1997). Online, Web-based learning environment for an Information systems course: Access logs, linearity and performance. Paper presented at the Information Systems Education Conference, Orlando, FL.
Zaiane, O. R. (2001). Web usage mining for a better Web-based learning environment. Paper presented at the 4th IASTED International Conference on Advanced Technology for Education (CATE'01), Banff, Canada.