The teacher and his deputy director True Light College in Hong Kong, Ka Tim Chu, wanted to understand the feelings of his students during the lesson. Now a new one platform learning that it uses AI technology, can monitor children's emotions as they take online lessons.
The software, called 4 Little Trees, created by Find Solution AI, a start up based in Hong Kong. While the use of AI technology to recognize emotions in schools has caused worry, its creator Viola Lam says it can make a virtual classroom as good as the real one if not better.
The schoolchildren work on tests and homework on the platform as part of the school curriculum. As they study, artificial intelligence measures the muscle tone on their faces through its camera computer or his tablet identifies emotions such as happiness, sadness, anger, surprise and fear.
The system also monitors how much time students need to answer the questions. Records the signs and their performance history. Creates reports on their strengths, weaknesses and motivation levels and predicts their grades. The program can be tailored to each student, targeting gaps in their knowledge and offering game-style tests designed to make learning more fun. Students perform 10% better on exams if they have learned to use 4 Little Trees, says Lam.
Lam, who was a teacher, remembers finding out that some of her students only had gaps when she saw the results of their exams.
4 Little Trees software was launched in 2017, with funding of $ 5 million, to give teachers the opportunity to better understand difficulties faced by their students. The number of schools using it in Hong Kong has increased from 34 to 83 in the last year. Prices range from $ 10 to $ 49 per student.
Lam says that technology is particularly useful for teachers during the pandemic because it allows them to remotely monitor their students' emotions as they teach.
Chu believes that the benefits of technology will continue after pandemic, because it reduces the burden on the administrator by creating and highlighting personalized tasks and tests. And unlike teachers, AI that reads expression can pay close attention to each student's emotions, even in a large classroom.
But technology that monitors children's faces raises concerns about it privacy.
At China, artificial intelligence that analyzes biometric data for monitoring purposes in schools and elsewhere has caused controversy.
Lam says 4 Little Trees records facial muscle data. This is how AI interprets emotional expressions, but does not videotape students' faces.
Ο Pascale Fung, says the director of the Artificial Intelligence Research Center at Hong Kong University of Science and Technology says "transparency" is the key to maintaining students' privacy. He says developers must obtain parental consent to collect student data and then "explain where this data will go."
Racial bias is also a serious issue for AI. Research shows that some emotional analysis technologies have difficulty detecting the emotions of darker-skinned people, in part because algorithm is formed and learns how to recognize emotions mainly from white persons.
Lam says she trains AI with facial data that matches students' demographics. So far, it has worked well in Hong Kong's predominantly Chinese society, but recognizes that more mixed communities could pose a greater challenge to the software.
Lam said Find Solution AI emotion recognition works with 85% accuracy in Hong Kong. Fung says algorithms with "very good settings" can correctly detect primary emotions, such as happiness and sadness, in up to 90% of cases.
However, more complex emotions, such as annoyance, excitement, or anxiety, may be more difficult to identify. As AI improves, Lam hopes to develop applications for businesses as well as schools to better understand the needs of participants and increase engagement in online meetings and seminars.