Semantic fuzzy mining: Enhancement of process models and event logs analysis from syntactic to conceptual level

The Application of a Semantic-Based Process Mining Framework on a Learning Process Domain

“…Therefore, in practice, PM poses some certain issue of semantics that limits its efficiency when handling large volume of events log from the complex educational systems [22][24] [2]. The authors in [22] argue that the semantic process mining [24][2] approach appears to be a promising area that can be explored in order to resolve those issues of understanding the different patterns or trace heterogeneity, and as such, to extract streamlined models that fits or represents the actual processes as performed in reality. Moreover, [22] believes that semantic annotation of the captured datasets can be utilized to address the challenge of interpreting the processes.…”

“…Essentially, we make use of the OWL Application Programming Interface (OWL API) to extract and load the inferred concepts from the defined ontology. Example of the inferred underlying concepts using the OWL API and the resulting ontologies is as shown in [23] and [24] and described in Section (V) of this paper.…”

“…Without a doubt, the procedures in Algorithm 2 shows the need for a well-defined semantic annotation process especially in developing such an ontology-based framework (SPMaAF) that supports semantic-based PM and analysis -by producing in an automatic manner the underlying taxonomies and/or properties the process instances share within the knowledge base [29] [24]. Thus, the semantic annotation process is necessary for concrete implementation of the SPMaAF including the further steps of enhancing the model as explained in [24]. According to [29] a semantically annotated graph is described as follows:…”

“…In summary, methods for semantic PM and analysis such as the SPMaAF in this paper -focuses on information about resources hidden within a process knowledge-base, and how they are related [2][23] [24] [31]. The semantic-based analysis allows the meaning of the domain entities and/or object properties to be enhanced through the use of property characteristics and classification of discoverable entities, to permit analysis of the extracted event logs based on concepts rather than event tags or labels about the process.…”

“…ontology classifications). Specifically, [24] and [32] perform semantic modelling and integration of the resulting process maps with annotated terms and then present the domain knowledge for the activities (i.e attributes or concepts) as defined within the ontology using process description languages such as the OWL [7] and SWRL [8]. Indeed, reasoning on ontological knowledge plays an important role in semantic representation of processes [33] by allowing for extraction and conversion of explicit information into some implicit information.…”