Discovering sequential concept patterns for behavioural diagnosis by interpreting web-page contents

As web-based courses become more popular, web systems can accumulate large amounts of log data. Because this data is generated by learners' behaviour while studying web-based courses, many researchers agree that analysing web logs could benefit learners, instructors and web-site managers. This paper describes a study that used data-mining techniques in order to analyse learners' online behaviour for the purpose of extracting concept patterns - by transforming general web logs to a content perspective. An important advantage of this approach is that it can be used to identify concept patterns based on learning behaviour - rather than the more conventional browsing patterns based on browsing behaviour.