Skip to main content Skip to navigation

A Combined Approach of Process Mining and Rule-based AI for Study Planning and Monitoring in Higher Education

Project Overview

The document explores the innovative application of generative AI in education through the AIStudyBuddy project, which combines process mining and rule-based artificial intelligence to improve study planning and monitoring in higher education. It introduces two key applications: StudyBuddy, designed for students, which offers personalized study plan recommendations derived from historical data, and BuddyAnalytics, aimed at study program designers, facilitating the analysis of study paths to enhance curriculum design based on data-driven insights. This integration of AI technologies addresses the complexities and deviations often encountered in student study paths, ultimately striving to boost academic success and ensure a more tailored educational experience for learners. The findings suggest that leveraging generative AI in this manner not only personalizes learning but also equips educators with the tools needed to refine educational programs, thereby fostering a more effective learning environment.

Key Applications

AIStudyBuddy (StudyBuddy and BuddyAnalytics)

Context: Higher Education, targeting students and study program designers across various disciplines, utilizing data from Campus Management Systems for improved study guidance.

Implementation: A combination of process mining techniques and rule-based AI to analyze data from Campus Management Systems, providing tailored recommendations for study planning and program design.

Outcomes: ['Improved individual study planning', 'Enhanced understanding of study paths', 'Data-driven feedback for both students and program designers']

Challenges: ['Complexity in modeling deviations', 'Need for accurate data representation', 'Handling exceptions in study plans']

Implementation Barriers

Data-related barrier

Limited access to comprehensive data from Campus Management Systems, which restricts the analysis capabilities.

Proposed Solutions: Integrate additional data from Learning Management Systems to provide a more complete view of student behavior.

Complexity barrier

The complexity of accurately modeling rules and exceptions in study plans due to variations in student situations.

Proposed Solutions: Utilize event calculus and answer set programming to effectively represent examination regulations and student event logs.

Project Team

Miriam Wagner

Researcher

Hayyan Helal

Researcher

Rene Roepke

Researcher

Sven Judel

Researcher

Jens Doveren

Researcher

Sergej Goerzen

Researcher

Pouya Soudmand

Researcher

Gerhard Lakemeyer

Researcher

Ulrik Schroeder

Researcher

Wil van der Aalst

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Miriam Wagner, Hayyan Helal, Rene Roepke, Sven Judel, Jens Doveren, Sergej Goerzen, Pouya Soudmand, Gerhard Lakemeyer, Ulrik Schroeder, Wil van der Aalst

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies