Researchers at the Hong Kong University of Science and Technology (HKUST) and China's Harbin Engineering University have created an artificial intelligence (AI) system that analyzes students' emotions based on video recordings of their facial expressions to measure their engagement level in a class.
The AI system was tested in a classroom of toddlers in Japan and a classroom of university students in Hong Kong. While the visual analytics system was successful in detecting obvious emotions like happiness, it often incorrectly reported anger or sadness in students who were focused on the lectures.
Said HKUST computer scientist Huamin Qu, "To address this issue, we need to add new emotion categories, relabel our data, and retrain the model."
From IEEE Spectrum
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA