Hyderabad, Jul 29 (INB) The popularity of children’s videos on YouTube does not necessarily reflect their educational value, according to a study by the Indian School of Business (ISB). The ISB has developed an artificial intelligence (AI)-based framework to evaluate the academic quality of online video content, it said in an official statement. The research, titled “Quantifying the Academic Quality of Children’s Videos Using Machine Comprehension”, was conducted by ISB Assistant Professor of Information Systems Sumeet Kumar along with Mallikarjuna Tupakula and Ashiqur R KhudaBukhsh of the Rochester Institute of Technology. The study has been published in the INFORMS Journal on Computing. The researchers analysed nearly 49,000 videos from 134 popular children’s YouTube channels using more than 6,300 curriculum-based question-answer pairs and benchmarked them against around 21,000 textbook questions covering grades 1 to 12, according to the statement. The study found that videos attracting higher viewership were not always those offering stronger educational value, underscoring a disconnect between children’s viewing habits and meaningful academic learning, it added. To address this, the researchers developed a machine comprehension-based model that evaluates whether a video’s spoken and visual content can correctly answer textbook-aligned questions. The AI model achieved an accuracy of up to 77.5 per cent, demonstrating its potential as a scalable tool for assessing the academic relevance of children’s digital content, according to the study. “Parents today face a digital deluge of content, making it difficult to distinguish between what is educational and what is simply engaging,” Kumar said, adding that the framework could help parents, educators and digital platforms prioritise videos that genuinely support learning. The study also found that while foundational topics such as basic measurement and language skills are relatively well represented on digital platforms, more advanced concepts, including scientific reasoning, remain underrepresented. According to the researchers, the findings could help improve content recommendation systems by incorporating educational value alongside engagement metrics and support better-informed decisions by parents and educators as digital videos become an increasingly important part of children’s learning.
