Profile

Eduard Frankford

PhD Researcher
University of Innsbruck
Department of Computer Science

ICT Building Room 3M02
Technikerstraße 21a
A-6020 Innsbruck
Austria - Europe

Email: Firstname.Secondname [AT_NOSPAM] uibk.ac.at

Google Scholar

Research Interests

Available Theses Topics

I provide guidance on topics suitable for seminars (SE), bachelor's (BSC), and master's (MSC) theses, primarily within the disciplines of computer science (CS), software engineering (SE), and information systems (IS). I mentor students from the University of Innsbruck and various other European institutions. Below is a compilation of potential thesis topics. Should any of these pique your interest, I welcome you to reach out.

Title Type Study
Introduction: This study reviews how large language models influence curricular design, teaching approaches, and assessment strategies in computer science education while incorporating ChatGPT in automated programming assessments.

Methodology:
  • Systematic Literature Review: Compile and analyze articles on curricular adaptations and ethical considerations.
  • Comparative Empirical Analysis: Assess student performance metrics before and after ChatGPT integration.
  • Integration of Findings: Combine literature insights with empirical data to derive actionable recommendations.
Introduction: This study explores chatbot interactions in programming assessments to uncover distinct user personas and evaluate the reliability of ChatGPT-generated feedback.

Methodology:
  • Data Extraction: Collect conversation metadata, linguistic features, sentiment cues, and engagement patterns.
  • User Persona Analysis: Identify and classify behavioral profiles based on interaction styles.
  • Performance Comparison: Evaluate student metrics before and after the integration of automated feedback.
  • Synthesis: Combine findings to assess the educational impact and reliability of AI-based feedback.
Introduction: This research introduces a novel approach to adaptive course design by using LLMs to generate personalized exercises that adjust content and difficulty according to user preferences within Artemis.

Methodology:
  • Literature Review: Investigate existing LLM-based exercise generation and evaluation frameworks.
  • Prompt Engineering: Develop precise strategies for directing the LLM to produce targeted exercises.
  • Pipeline Implementation: Create an integrated system for data collection, exercise generation, filtering, and evaluation.
  • Feedback Integration: Incorporate instructor evaluations to iteratively improve exercise quality.
  • Deployment: Test the pipeline by generating and exporting an updated Artemis course with adaptive tasks.
Introduction: This study addresses the rising issue of LLM-assisted cheating in university assessments by reviewing current countermeasures and their efficacy in preserving academic integrity.

Methodology:
  • Problem Definition: Outline key research questions related to LLM-assisted academic dishonesty.
  • Systematic Literature Review: Aggregate and categorize existing strategies and technological measures.
  • Critical Evaluation: Assess the effectiveness, limitations, and ethical concerns of each strategy.
  • Research Gap Analysis: Identify insufficiently addressed areas and suggest avenues for further investigation.

Once your bachelor's thesis topic has been confirmed, please prepare to present your project proposal during the "Seminar mit Bachelorarbeit". For tips on crafting an effective initial presentation, refer to this guide.

Publications