Bespoke system creates industry-specific lecture videos with low cost
Bespoke: Generating MOOC-Quality Industry-Personalized Lecture Videos at Scale
Human-Computer Interaction
Summary
Many people from different jobs watch the same online lectures, even though they use the material differently at work. The authors built Bespoke, a system that takes a lecture transcript and makes a new video tailored to a particular industry, with customized slides, narration, and charts. They tested it on graduate-level courses and found experts thought most videos matched the quality of standard online classes, at a low cost per minute. The videos worked well across different industries and video lengths.
What this means in practice
- •For corporate training teams: Create customized training videos from existing lectures tailored to specific industries and time limits to improve employee learning relevance.
- •For online education platforms: Automatically generate industry-personalized versions of existing course videos to diversify offerings without re-recording content.$Commercial implications: Enables platforms to sell specialized course videos to corporate clients needing tailored training content, reducing production costs.
Authors
Romain Puech, Dewang Kumar Agarwal, Antonio Santamaría Escobar, Dimitris Bertsimas
Abstract
Lifelong learners from different industries often watch the same recorded lecture, even when they will apply the material in different workplaces. We present Bespoke, a system that takes the transcript of an existing lecture and generates a new video customized to a target industry and duration, with new slides, narration, and charts. From 31 graduate lectures in analytics, machine learning, and optimization, we generated 209 videos for these three industries, plus a generic-audience version of each lecture. Twenty-five experts in the corresponding domains rated 92 videos on a five-point rubric. They judged 87% at or above the rubric midpoint corresponding to ``a standard MOOC lecture's quality'' (mean overall score 3.42 out of 5; 48% scored 4 or above). Overall quality was similar across industries, durations, and a 21-lecture held-out set unused while developing the system, at about \$0.22 API cost per minute of video.