pAIpercast: Paper to podcast
Explore outputs from this project supported by the AI Teaching and Learning Exploratory Fund in 2024-25
Project members
Stephen Taylor, Delia O’Rourke, Bana Alamad (MSD).
Project summary
Introducing an AI-driven solution that transforms academic papers into engaging conversational podcasts, improving accessibility, engagement, and time-efficient knowledge acquisition.
View final project report (PDF)
AI in Teaching and Learning at Oxford Knowledge Exchange Forum, 9 July 2025
Findings from projects supported by the AI Teaching and Learning Exploratory Fund in 2024–25 were presented at the AI in Teaching and Learning at Oxford Knowledge Exchange Forum at Saïd Business School on Wednesday, 9 July 2025.
Project team members each presented a lightning talk to all event participants, and hosted a series of small group discussions.
Follow the links below to view the lightning talk recording and presentation slides for this project.
View presentation slides (PDF)
Case study
PAIpercast, a ground-breaking prototype, transforms complex research papers into dynamic, multi-voice, conversational podcasts using Open AI services. This case study evaluated its impact on student learning and engagement within a medical-focused MSc program's Journal Clubs (JCs).
Case study overview and rationale
We integrated pAIpercast podcasts into three Journal Clubs during Trinity Term 2025. The tool generated short podcasts based on academic papers relevant to each JC. The goal was to assess if listening to these podcasts improved students' understanding of the articles, their confidence, and their overall engagement in JC discussions. We also evaluated pAIpercast's customisable features, such as podcast length and style.
We surveyed both students and tutors to gather feedback on the tool's effectiveness in preparing for JCs, where student engagement can often fluctuate.
Evaluation results
Student Learning: Students generally rated the podcasts highly, with a 4/5 effectiveness score for helping them understand academic content.
Tutor Perception: Tutors recognised the value of the tool, noting that a critical analysis or a mixture of critical and conversational styles made the literature more accessible. One tutor remarked that pAIpercast could be "invaluable" for students with additional needs (e.g., dyslexia) by digesting papers into manageable sizes and introducing complex ideas briefly.
Key Findings: Overall, the project was perceived positively by students and colleagues who participated in the trial.
Challenges and future directions
We faced challenges with low attendance and volunteer participation, possibly due to the JCs being optional and scheduled during student research periods.In the future, we will consider making JCs compulsory or adjusting timing to improve participation. We plan to expand our evaluation to include students and researchers across various disciplines within the University, ensuring continued feedback from both students and tutors for continued development and critical analysis of the pAIpercast.
