Paper: Enhancing Peer Feedback in MarkEd

Inspired by a semester spent marking second-year students' essays, I proposed my dissertation project aimed at improving assessment practices in education.

Under the guidance of my amazing supervisors

Cristina Alexandru ↗ and

Aurora Constatin ↗, we developed a tool addressing common issues in peer assessment. By combining structured moderation from human markers with AI-generated guidance, educators now have a toolkit for running more effective and reflective peer-review assignments.

The system was trialled during a large second-year course at the University of Edinburgh involving around 200 students. The results were really promising: notably, over 75% of students agreed that the AI-supported tools helped them reflect more deeply on the feedback they provided. The dissertation itself received a grade of Outstanding (93%).

From this dissertation, we wrote a paper recently accepted for presentation at the UK and Ireland Computing Education Research (UKICER) 2025 conference, with publication forthcoming in the conference proceedings.

I'll link the paper as soon as it's out: watch this space!

Sincerely,
Tomas