Student Outcomes and the 2 Sigma Problem
In 1984, researcher Benjamin Bloom issued a challenge to educators—find methods of group instruction as effective as 1:1 tutoring.
In fact, it was Bloom himself that found that 1:1 tutoring significantly increased student outcomes. Known as the 2 Sigma Problem, studies across grade levels and in different schools found similar results: students who received tutoring performed two standard deviations better than students who learned through conventional instruction.
Almost 35 years later, Intel, and partners are applying artificial intelligence and machine learning to solutions that help transform personalized learning and bring us closer to meeting Bloom’s challenge.
Personalized Learning Through Artificial Intelligence
Computers in the classroom have traditionally been seen as merely tools that process inputs provided by the users. A convergence of overlapping technology is making new usages possible. Intel and partners are enabling artificial intelligence at the edge, using the computing power of Intel CPUs to support artificial intelligence innovations with deep learning capabilities that can now know users at a higher level – not merely interpreting user commands but also understanding user behaviors and emotions. The new vision is a classroom PC that collects multiple points of input and output, providing analytics in real-time that lets teachers understand student engagement.
Research has shown that performance is highly correlated with engagement.1 Intel is currently studying artificial intelligence application in the classroom using multi-modal sensing to gather data on three primary inputs to better predict engagement during a class session.
Appearance – Computer cameras used to extract facial landmarks, upper body, and head movement and pose
Interaction – How the student uses traditional input devices (keyboard, mouse)
Time to action – how long is the student taking to complete tasks or take action on a learning platform
Students in the sessions were asked to work on the same online course work. Instructors, armed with a dashboard providing real-time engagement analytics, were able to detect which students required additional 1:1 instruction. By identifying a student’s emotional state, real-time analytics helped instructors pinpoint moments of confusion, and intervene students who otherwise may have been less inclined or too shy to ask for help. In turn, empowering teachers and parents to foresee at-risk students and provide support faster.
The Next Contribution
Artificial intelligence solutions are paving the way to solve highly complex education challenges, identify learning patterns and better predict student behavior and outcomes.
Intel has the industry’s most comprehensive suite of hardware and software technologies that deliver broad capabilities and support diverse approaches for artificial intelligence. Rising use cases for artificial intelligence in education include generating personalized learning plans, real-time assessment and feedback, supporting teachers on time consuming tasks, and extended learning beyond the classroom.