In our paper we are examining the application of process mining techniques in the development of adaptive e-learning systems such as Intelligent Tutoring Systems. Process mining techniques can discover business process models from event log data. Here, we will use process mining to discover and add new useful tutoring sessions (learning paths) to our adaptive e- learning system. E- learning knowledge base is an ontology (union of taxonomies) of a chosen domain. Using data in the ontology we build a directed acyclic graph with nodes (states) and labeled transitions (questions), or more formally, as a deterministic finite automaton (DFA). Each tutoring session is a run of the DFA, or in process mining terminology: one learning process model. We will apply well- known Angluin's L* algorithm on the data from e- learning system log files to discover new useful tutoring sessions which can be added to the e- learning system DFA. We will present use case examples based on our e-learning system used on our course Fundamentals of Electrical Engineering.
