Virginia Tech
CELLOS: Capturing and Elaborating Live-coding Lectures into Organized Summaries
Abstract
dc:description.abstractgeneralLive coding is a common teaching method in computer science where instructors write and explain code in real time during class. While students often find these sessions engaging, it can be difficult to review what happened afterward because lecture recordings, slides, and code files rarely capture the full explanation or step-by-step process. To better understand this challenge, we interviewed computer science instructors who regularly teach with live coding. Based on their feedback, we developed an AI-powered system that records both the instructor's coding and spoken explanations, then automatically creates organized lecture notes that include text, code, and images. We compared our system with two other approaches: a simple AI prompt that summarizes lecture recordings and a commercial AI note-taking tool. Instructors found that our system produced clearer, more complete, and better-organized notes, making it easier for students to review lectures on their own. Our findings suggest that AI can help students learn more effectively by making live coding lectures easier to revisit after class.
Degree
thesis:*- Name thesis:degree_name
- Master of Science
- Level thesis:degree_level
- masters
- Discipline thesis:degree_discipline
- Computer Science & Applications
- Department dc:contributor.department
- Computer Science and Applications
- Grantor dc:publisher
- Virginia Tech
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zheng, Yuhang
- Chair dc:contributor.committeechair
-
- Lee, Sang Won
- Committee members dc:contributor.committeemember
-
- Rho, Ha Rim
- Chen, Yan
Subjects
dc:subject × 2Rights
dc:rights- Statement dc:rights
-
- In Copyright
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Other
- vt_gsexam:47526