2025 ASEE Annual Conference & Exposition

Snackable Study: Boosting Micro-learning with Bite-Size Videos

Presented at DSAI Technical Session 1: K–12 and Early Exposure to Data Science and AI

Post-COVID, university class attendance has dropped to historic lows, with similar patterns seen in certain classes, where only 40% of students attend by the first month of the semester. Despite efforts to improve attendance, many students rely on recorded lectures and notes, often avoiding the lengthy 50 to 75-minute videos. As a result, students frequently seek help during office hours for concepts already covered in these lectures, increasing the pressure on instructors and negatively impacting student performance.

Research shows that students prefer shorter video formats, like those popularized by YouTube and TikTok, which improve memory retention and learning outcomes. Videos under five minutes engage students more effectively by delivering concise, targeted content, helping them retain knowledge and focus on task-relevant activities.

We propose an AI-driven solution that automatically extracts video segments from recorded lectures based on student queries to address the time-consuming nature of creating these short videos. The system uses advanced natural language processing and context-aware retrieval to match student questions with relevant lecture content, extracting personalized, bite-sized video clips. This creates a scalable, personalized learning environment that enhances student engagement and alleviates pressure on educators, paving the way for a more efficient teaching method across other courses.

Authors

Sri Krishna Chaitanya Velamakanni Pennsylvania State University [biography]

Sri Krishna Chaitanya is a Software Engineer at Walmart, where he focuses on enterprise backend payment applications. He holds a Master’s degree in Computer Science from The Pennsylvania State University. His research interests lie at the intersection of Natural Language Processing (NLP), financial technology (fintech), and the applications of Large Language Models (LLMs).
Suman Saha Pennsylvania State University [biography]

Suman Saha received a Ph.D. degree in computer science from Pierre and Marie Curie University, Paris, France, in 2013.

He is an Assistant Teaching Professor at Pennsylvania State University, University Park, PA, USA. Since 2016, he has been involved in academia. Before his current role with Pennsylvania State University, he taught at Illinois Institute of Technology, Chicago, IL, USA, and Illinois State University, Normal, IL, USA.

Dr. Saha received the distinguished William C. Carter Award for his substantial contributions to dependable and secure computing during his doctoral studies. He has held positions at several prestigious National and International Research Labs, including Microsoft, Cambridge, U.K., Harvard University, Cambridge, USA, and the National Institute for Research in Digital Science and Technology (Inria), Paris, France.

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 22, 2025, and to all visitors after the conference ends on June 25, 2025

« View session

For those interested in:

computer science
engineering technology
Faculty
undergraduate