Figure - available from: Journal of Intelligent Information Systems
This content is subject to copyright. Terms and conditions apply.
Source publication
Today’s universities are more and more focused on improving their educational programs and supporting their students throughout their academic journey. A key aspect of such an effort is understanding which factors contribute to poor students’ performance. This research illustrates how educational process mining techniques can be used to effectively...
Similar publications
Citations
... It requires defining a process model that reflects the trajectory of students. Cases are usually actual students' trajectories in which events of the discovered process represent courses, for example, in (Anuwatvisit et al. 2012;Ayutaya et al. 2012;Caballero et al. 2018;Cameranesi et al. 2017;Hobeck et al. 2022;Martinez et al. 2021;Schulte et al. 2017;Wang and Zaïane 2015), or certain curriculum milestones such as the end of a semester (Diamantini et al. 2024a(Diamantini et al. , 2024bPotena et al. 2023). However, the semantics of an event can be conceived from different perspectives, not only from a curricular standpoint, for example, the courses a student approves, but also from a contextual perspective, for example, graduation in time, late dropouts, or the number of pending studies. ...
... Since a trajectory refers both to a student's path and a set of students, in some cases, there is an a priori clustering of traces based on considering additional information, for example, demographic information or students' performance characteristics, which sometimes requires additional data mining tools (Diamantini et al. 2024a;Salazar et al. 2019a). In other cases, clustering is performed beforehand during the analysis. ...
... In (Bendatu and Yahya 2015), the authors check the curriculum design using sequence matching analysis to the actual trajectories using sequence matching analysis. Finally, in (Diamantini et al. 2024a), the authors use a cost-based conformance-checking technique leveraging the fitness metric by considering the cost of skipping and inserting activities. An additional perspective to conformance-checking is followed in (Rennert et al. 2024) in which partial orders are used to relax the constraints of strictly ordered traces, and alignments can be computed without requiring a strict order in which courses are offered. ...
Educational Process Mining (EPM) is a data analysis technique that is used to improve educational processes. It is based on Process Mining (PM), which involves gathering records (logs) of events to discover process models and analyze the data from a process‐centric perspective. One specific application of EPM is curriculum mining, which focuses on understanding the learning program students follow to achieve educational goals. This is important for institutional curriculum decision‐making and quality improvement. Therefore, academic institutions can benefit from organizing the existing techniques, capabilities, and limitations. We conducted a systematic literature review to identify works on applying PM to curricular analysis and provide insights for further research. We reviewed 27 primary studies published across seven major databases. Our analysis classified these studies into five main research objectives: discovery of educational trajectories, identification of deviations in student behavior, bottleneck analysis, dropout/stopout analysis, and generation of recommendations. Key findings highlight challenges such as standardization to facilitate cross‐university analysis, better integration of process and data mining techniques, and improved tools for educational stakeholders. This review provides a comprehensive overview of the current landscape in curricular process mining and outlines specific research opportunities to support more robust and actionable curricular analyses in educational settings.
