The advances in Information and Communication Technologies (ICT) have introduced e-learning, an alternative mode of learning, which positively affects the way teaching and learning take place by enabling both educators and students to use their limited time effectively (Delacey & Leonard, 2002; Radcliffe, 2002; Starr, 1977). E-learning is technology-based learning, such as computer-based learning, web-based learning, virtual classroom, and digital collaboration. E-learning describes the ability to electronically transfer, manage, support, and supervise learning and educational materials (Cone & Robinson, 2001; Normark & Cetindamar, 2005). Many authors have discussed the way in which elearning can be used for the delivery of training, assessment, and support (Fichter, 2002). E-learning has made considerable progress since the 1980s, attributable in large measure to technological developments.
Nowadays, the variety of different kinds of E-learning systems is very large. There are systems which support individual learning, collaborative learning, learning content management, learning activity management, formal learning, informal learning, and workplace learning.
One weakness of the E-learning systems is the lack of exploitation of the acquired information due to its volume. Most of the time, these systems produce reports with statistical data, which do not help instructors to draw useful conclusions either about the course or about the students. Moreover, the existing e-learning platforms do not offer concrete tools for the assessment of user actions and course educational content. To enable educators to improve their course and learners to acquire more knowledge, in our experiment two means of course evaluation are used: metrics and questionnaires.
Server log files store information containing the page requests of each individual user (Ueno, 2002). Data mining techniques have been used to discover the sequential patterns of students' web usage after the analysis of log files data (Romero & Ventura, 2007). The extraction of sequential patterns has been proven to be particularly useful and has been applied to many different educational tasks (Romero, Gutierez, Freire, & Ventura, 2008).
The objectives of this paper are the analysis of the log file of an eLearning system and the deduction of useful conclusions. Indexes, metrics, and one algorithm for classification, which were firstly introduced by the authors, are also used (Valsamidis, Kazanidis, Kontogiannis, & Karakos, 2010; Valsamidis, Kontogiannis, Kazanidis, & Karakos, 2010). Finally, data mining techniques were applied disclosing interesting insights.
The paper initially makes a literature review and follows with the background theory, the proposed methodology, the application of the methodology with the use of a case study relating to the eLearning, the practical implications of the results, and the conclusions along with future directions.
There are several studies that show the impact of data mining on eLearning. Whilst data mining methods have been systematically used in a lot of e-commercial applications, their utilization is still lower in the E-learning systems (Zaiane, 2001). It is important to notice that traditional educational data sets are normally small (Hamalainen & Vinni, 2006) if we compare them to files used in other data mining fields such as e-commerce applications that involve thousands of clients (Srinivasa, 2005). This is due to the typical, relatively small class size although it varies depending on the type of the course (elementary, primary, adult, higher, tertiary, academic, or/and special education); the corresponding transactions are therefore also fewer. The user model is also different in both systems (Romero & Ventura, 2007).
Very interesting is the iterative methodology to develop and carry out maintenance of web-based courses, in which a specific data mining step was added (Garcia, Romero, Ventura, & de Castro, 2008). …