Systems of adaptive learning use various innovations in the field of ICT, such as artificial intelligence and machine learning in order to ensure personalization in learning. This approach to education prioritizes meeting individual needs of the students, “adapting” the material and methods to his or her personal traits and learning habits (Mavroudi et al., 2017).
Most systems of adaptive learning share three main components: content model, which includes certain subjects, detailed learning goals and identification of tasks that need to be completed; learner model, whereby the system measures the abilities and skills of the learner in acquiring a particular topic; and a teaching model, which identifies the way in which the system chooses a particular topic for a certain learner at a certain point in (Oxman and Wong, 2014).
Studies identify that there is a notable positive effect of adaptive learning on performance of students at schools and universities. For instance, Wang et al. (2020) conducted a research in Chinese schools. Their research showed that adaptive learning was more effective than learning in large groups or in smaller groups, even if these groups were taught by expert teachers.
The case of the United States
US Department of Education Office of Educational Technology offered the following definition of adaptive learning in 2013: «Digital learning systems are considered adaptive when they can dynamically change to better suit the learning in response to information collected during the course of learning rather than on the basis of preexisting information such as a learner’s gender, age, or achievement test score».
During the initial stages, the US government offered scholarships to develop adaptive learning systems in K-12 learning (pre-school and secondary education). Systems collectively known as Intelligent Tutoring Systems were a result of this work. The more notable systems include Cognitive Tutor by Carnegie Learning and ALEKS, developed as a result of research in UC-Irvine and New York University. Both focus on math and were developed using findings from cognitive theories. Cognitive Tutor has 600,000 active users in grades 6-12 in 2014, ALEKS was used by approximately a million students in over 900 schools and districts. Research showed that ALEKS led to increase in attendance and performance of students in math classes. Adaptive learning gained a boost in development with various government initiatives, such as Race to the Top, Common Core Standards, as well as development of cloud computing technologies (Oxman and Wong, 2014).
The case of China
Adaptive learning is one of the more relevant solutions to some of the problems faced by the education system of China. First of all, the country of 1,4 billion people is home to the largest student cohort, as well as the largest average number of children in class (52 students on average, which is significantly higher than 16.7 children in American schools). Such a huge number of students in class means that teachers would find it difficult to personalize their instruction to the needs of each and every child in their class, which results in more challenges for students from vulnerable socio-economic backgrounds. Chinese families rely on services of tutors in order to address this problem; however, studies demonstrate that this is not sufficient to improve student performance. China also faces a serious challenge due to a large gap in performance between cities and rural areas, with a difference equivalent to two years of schooling, according to nation-wide research. Adaptive learning can serve as a potential solution to compensate for a deficit of qualified teaching staff in rural schools (Wang et al., 2020).
A notable case of adaptive learning is the use of Squirrel AI Learning, which was launched in 2016 and offers material in subjects like math, English, Mandarin Chinese, physics, and chemistry to over 2 million students in China. Study results show that students that were part of the group selected to participate in adaptive learning showed better results compared to students that were learning in class, regardless of class size (Wang et al., 2020).
References:
Mavroudi, A., Giannakos, M., & Krogstie, J. (2018). Supporting adaptive learning pathways through the use of learning analytics: developments, challenges and future opportunities. Interactive Learning Environments, 26(2), 206-220.
Oxman, S. & Wong, W. (2014). White paper: Adaptive learning systems. Integrated Education Solutions, 2-30.
Wang, S., Christensen, C., Cui, W., Tong, R., Yarnall, L., Shear, L., & Feng, M. (2020). When adaptive learning is effective learning: comparison of an adaptive learning system to teacher-led instruction. Interactive Learning Environments, 1-11.