PhD Candidate - Software Engineering

PhD Candidate at the University of Stuttgart in Software Engineering

Stuttgart

Master of Science (M.Sc.) - Software Engineering

Master study at the University of Stuttgart in Software Engineering

Final grade: 1,2

Master's thesis: Interdisciplinary Composition of E-Learning Platforms based on Reusable Low-Code Adapters

Stuttgart

Graduate Direct Exchange (GDX) - Computer Science and Leadership

Study abroad program at the University of Kansas in Computer Science and Leadership

GPA: 4,0 (USA)

Lawrence, KS (USA)

Bachelor of Science (B.Sc.) - Applied Computer Science

Dual study at the University of Telecommunications Leipzig in Applied Computer Science in cooperation with Deutsche Telekom AG

Final grade: 1,9

Bachelor's thesis: Investigation and Evaluation of an Onshore/Offshore IDE solution (Eclipse) based on the IT4IT standard

Leipzig

High school graduation

High school graduation at Lise-Meitner-Gymnasium

Maxdorf

The increasing importance of programming skills for various professions highlights the necessity of laying solid foundations for these skills in school. One critical step when learning programming is code tracing, i.e., the ability to analyze program code to predict the data changes when the code is executed. Considering the diverse levels of prior knowledge in computer science classes, it is essential to implement tailored teaching approaches, which can enhance the respective learning outcomes. ... To create personalized learning paths, we developed the tutoring system Feedback Buddy that teaches if-else branches, for loops, and combinations of them using tracing tables. Thereby, the Feedback Buddy adapts its feedback and task difficulty based on learners’ affective, cognitive, and metacognitive states. Extending former systems, our approach focuses on school education and uses growth mindset feedback. Evaluation with 10th grade students in computer science classes yielded positive results, affirming the usability and usefulness of the Feedback Buddy in secondary school education.

Show Publication

Lecturers are increasingly attempting to use large language models (LLMs) to simplify and make the creation of exercises for students more efficient. Efforts are also being made to automate the exercise creation process in software engineering (SE) education. This study explores the use of advanced LLMs, including GPT-4 and LaMDA, for automated programming exercise creation in higher education and compares the results with related work using GPT-3.5-turbo. ... Utilizing applications such as ChatGPT, Bing AI Chat, and Google Bard, we identify LLMs capable of initiating different exercise designs. However, manual refinement is crucial for accuracy. Common error patterns across LLMs highlight challenges in complex programming concepts, while specific strengths in various topics showcase model distinctions. This research underscores LLMs' value in exercise generation, emphasizing the critical role of human supervision in refining these processes. Our concise insights cater to educators, practitioners, and other researchers seeking to enhance SE education through LLM applications.

Show Publication

The integration of Artificial Intelligence (AI) tech-nologies into educational settings has paved the way for inno-vative teaching and learning approaches. In Software Engineering (SE) education, using Unified Modeling Language (UML) diagrams is a fundamental teaching element for understanding complex software systems. This research addresses ChatGPT's ability to utilize UML class and sequence diagrams to create SE modeling exercises. ... We use ChatGPT to generate exercises based on the information from uploaded UML diagrams by analyzing textual UML representations such as Mermaid and graphical diagrams. The research explores ChatGPT's ability to synthesize UML-specific information from class and sequence diagrams, enabling the generation of various exercises tailored to strengthen conceptual understanding and practical application. Furthermore, we investigate generating graphical UML class and sequence diagrams based on natural language as input. By bridging the gap between AI -driven natural language understanding and the comprehension of UML diagrams, this study highlights the potential of ChatGPT to improve SE education. Our concise findings address educators, practitioners, and other researchers engaged in the field of SE education with a special focus on UML.

Show Publication

Modern software systems often consist of independently developed components, e.g., libraries or (micro-)services, that can be combined to form a larger architecture. Many of these components are developed externally, i.e., in other projects by other teams, which is particularly the case in service-oriented architectures. Even though the components are independently developed, bugs may arise that propagate along the call chains, which sometimes negatively affect the calling components. ... However, as such components are typically managed in separate issue management systems (IMS), identifying that a downstream component is affected by an upstream component’s issues is complex and time-consuming. Even though some scientific works and IMS forums discuss how to manage such cross-component issues, there is no systematic study on the state of practice and the challenges of issue management when different components are affected. Therefore, this study aims to determine which types of components are usually included in modern software projects, how developers identify and manage issue propagation between components, and how often they face such propagations. To get these insights, we conducted an empirical study through a questionnaire with 64 industry experts and open-source contributors and interviewed seven of them. Our key takeaways help researchers and software engineers to understand possible impacts and to improve cross-component issue management. We identified, for example, that related issues currently are non-semantically linked via URLs in issue comments.

Show Publication

Nowadays, learning management systems (LMSs) are established tools in higher education, especially in the domain of software engineering (SE). However, the potential of such educational technologies has not been fully exploited, as student performance in SE education is still strongly dependent on feedback from time-constrained lecturers and tutors. ... Moreover, current LMSs are not designed for SE courses, as external SE tools are required to fulfill the requirements of lecturers such as programming and UML modeling features. Evolving these LMSs in the direction of intelligent tutoring could assist students in receiving automatic, individual feedback from the LMSs on their learning performance at any time. Also, gamified learning elements can serve to motivate students to engage with SE materials. Therefore, this paper presents an approach combining learning analytics, feedback, and interactive learning such as gamification in one LMS designed for SE education. The system could thus address diverse students with different backgrounds and motivational aspects and provide appropriate individual support to ensure effective SE education.

Show Publication

Learning management systems (LMSs) are established tools in higher education, especially in the field of software engineering~(SE). The onset of the COVID-19 pandemic further amplified the utilization of these systems, which necessitated their integration into educational curricula for both lecturers and students. ... However, adopting LMSs within SE education has presented distinctive challenges impeding their seamless incorporation into the courses. This paper aims to scrutinize the challenges and requirements encountered by professors, lecturers, and students in the domain of SE education when using LMSs. We conducted an empirical study that included (i) a survey with 47 professors/lecturers and 133 students, (ii) an analysis of the ensuing data, and (iii) 18 additional interviews conducted with professors and lecturers to delve into nuanced variations in viewpoints. The findings derived from our study reveal that the challenges and requirements pertaining to LMSs are rather specific depending on the scope and size of the respective courses. Nevertheless, many participants have a consensus on numerous challenges and requirements for improving certain features of LMSs in order to improve their usage in SE education. The findings are valuable for advancing research and development in the field of LMSs and provide guidance for lecturers in SE education.

Show Publication

Self-assessment quizzes after lectures, educational videos, or chapters are a commonly used method in software engineering (SE) education to allow students to test the knowledge they have gained. However, creating these quizzes is time-consuming, cognitively exhausting, and complex, as an expert in the field needs to create the quizzes and review the lecture material for validity. ... Therefore, this paper presents a concept to automatically generate self-assessment quizzes based on lecture material using a large language model (LLM) to reduce lecturers' workload and simplify the general quiz creation process. The developed prototype was handed to experts, who subsequently evaluated the approach. The results show that automatic quiz generation saves time, and the quizzes cover the delivered lecture material well. However, the generated quizzes often lack originality and versatility. Therefore, further prompt engineering might be required to achieve more elaborate results.

Show Publication

In recent years, artificial intelligence (AI) has been increasingly used in education and supports teachers in creating educational material and students in their learning progress. AI-driven learning support has recently been further strengthened by the release of ChatGPT, in which users can retrieve explanations for various concepts in a few minutes through chat. ... However, to what extent the use of AI models, such as ChatGPT, is suitable for the creation of didactically and content-wise good exercises for programming courses is not yet known. Therefore, in this paper, we investigate the use of AI-generated exercises for beginner and intermediate programming courses in higher education using ChatGPT. We created 12 exercise sheets with ChatGPT for a beginner to intermediate programming course focusing on the objects-first approach. We report our process, prompts, and experience using ChatGPT for this task and outline good practices we identified. The generated exercises are assessed and revised, primarily using ChatGPT, until they met the requirements of the programming course. We assessed the quality of these exercises by using them in our external teaching assignment course at the University of Education Ludwigsburg and let the students evaluate them. Results indicate the quality of the generated exercises and the time-saving for creating them using ChatGPT. However, our experience showed that while it is fast to generate a good version of an exercise, almost every exercise requires minor manual changes to improve its quality.

Show Publication

Intelligent Tutoring Systems (ITSs) are increasingly used in modern education to automatically give students individual feedback on their performance. The advantage for students is fast individual feedback on their answers to asked questions, while lecturers benefit from considerable time savings and easy delivery of educational material. Of course, it is important that the provided feedback is as effective as direct feedback from the lecturer. ... However, in digital teaching, lecturers cannot assess the student’s knowledge precisely but can only provide information on which questions were answered correctly and incorrectly. Therefore, this paper presents a concept for integrating ITS elements into the gamified e-learning platform IT-REX so that the feedback quality can be improved to support students in the best possible way.

Show Publication

Digital learning is becoming increasingly important, especially in situations when students cannot attend presence lectures as we experienced during the Covid-19 pandemic. However, while there are platforms that support generic learning concepts such as multiple-choice questions, we believe that the first semesters of computer science courses can benefit from tailored learning platforms that support IT-specific learning. For example, programming tasks that are automatically checked for correctness. ... Moreover, in times when students cannot meet each other, self-organization and motivation quickly become severe problems. Therefore, this paper presents a vision for a gamified e-Learning platform specialized for the first semesters of computer science courses.

Show Publication