The Empirical Analysis of the Comprehensibility of Process Models created by Process Mining

Ulm University

MA Abschlussvortrag, Jana Bühler, Ort: Online, Datum: 05.10.2021, Zeit: 11:30 Uhr

Companies use process models to specify their operational processes. With the help of process models, the business processes in a company are analysed, and attempts are made to identify and eliminate bottlenecks and thus optimise the business processes.
The discipline of process mining makes the identification of the actual state of business processes visible and enables them to be examined. Process discovery is an important part of process mining, and various tools and algorithms can be used and which lead to different process visualisations. The execution of business processes generates so-called event logs, which are used to create process visualisations. The type of process visualisation has a major influence on the comprehensibility of rocess models.
The objective of this thesis is to investigate the comprehensibility of process models generated by process mining. For this purpose, an exploratory eye-tracking study is conducted with fifteen subjects. The study examined process models from two scenarios - a vaccination process and an insurance process. The corresponding process models are created manually, and event logs were generated from them using self-created applications. These event logs are loaded into the process mining tools Celonis Snap, Disco, ProM, Apromore and PM4Py and process models are generated from them. A selection of the resulting process models is then tested for comprehensibility in the user study. The analysis of variance (ANOVA) shows no significant differences between the different generated process models. Finally, with the help of the Pearson correlation, the subjective ranking of the subjects is high significant related to the level of acceptability and cognitive load. The correlation between the time spent looking at the process models, and the number of correctly answered comprehension questions is interesting. From this correlation, it can be concluded that understanding process models requires a certain amount of time and depends on the experience of the subject. An astonishing result of the study is that the quality between manually created models and models generated by process mining is similarly high. Despite interesting results, further studies are needed, as the study is confronted with some limitations (in particular the number of participants). The results can be used as a basis for future studies to expand the field of research further.