Towards Automated Slide Augmentation to Discover Credible and Relevant Links

Learning from concise educational materials, such as lecture notes and presentation slides, often prompts students to seek additional resources. Newcomers to a subject may struggle to find the best keywords or lack confidence in the credibility of the supplementary materials they discover. To address these problems, we introduce Slide++, an automated tool that identifies keywords from lecture slides, and uses them to search for relevant links, videos, and Q&As. This interactive website integrates the original slides with recommended resources, and further allows instructors to ‘pin’ the most important ones. To evaluate the effectiveness of the tool, we trialled the system in four undergraduate computing courses, and invited students to share their experiences via a survey and focus groups at the end of the term. Students shared that they found the generated links to be credible, relevant, and sufficient, and that they became more confident in their understanding of the courses. We reflect on these insights, our experience of using Slide++, and explore how Large Language Models might mitigate some augmentation challenges.