Semantic Process Mining Towards Discovery and Enhancement of Learning Model Analysis
Contributor(s)School of Architecture Computing and Engineering [University of East London] ; University of East London (UEL)
Centre Génie Industriel (CGI) ; IMT École nationale supérieure des Mines d'Albi-Carmaux (IMT Mines Albi)
[SPI] Engineering Sciences [physics]
Full recordShow full item record
Abstract2015 IEEE 17th International Conference on High Performance Computing and Communications (HPCC), Int Symposium Cyberspace Safety & Secur, New York, NY, AUG 24-26, 2016
Process mining algorithms use event logs to learn and reason about processes by technically coupling event history data and process models. During the execution of a learning process, several events occur which are of interest and/or necessary for completing and achieving a learning goal. The work in this paper describes a Semantic Process Mining approach directed towards automated learning. The proposed approach involves the extraction of process history data from learning execution environments, which is then followed by submitting the resulting eXtensible Event Streams (XES) and Mining eXtensible Markup Language (MXML) format to the process analytics environment for mining and further analysis. The XES and MXML data logs are enriched by using Semantic Annotations that references concepts in an Ontology specifically designed for representing learning processes. This involves the identification and modelling of data about different users. The approach focuses on augmenting information values of the resulting model based on individual learner profiles. A series of validation experiments were conducted in order to prove how Semantic Process Mining can be utilized to address the problem of analyzing concepts and relationships amongst learning objects, which also aid in discovering new and enhancement of existing learning processes. To this end, we demonstrate how data from learning processes can be extracted, semantically prepared, and transformed into mining executable formats for improved analysis.
DOI : 10.1109/HPCC-CSS-ICESS.2015.164