During lockdown, AI research discovers that ongoing studying became a more prevalent practice.

According to a study by the Universidad Operta de Catalunya (UOC), the Eurecat Technology Center and the Autonomous University of Madrid, published in Plus oneStudents worked continuously during the epidemic, which improved their results.

Data analysis conducted over five academic years shows that continuous study, that is, study that begins at least three months before exams, is the best way to get good grades. This means that determining how students study helps predict their future performance.

The study authors used artificial intelligence (AI) to predict results ahead of time, enabling them to help students who are likely to do poorly. As forewarned, the students were able to revise their preparation methods and change their learning strategies if they were not productive. It also enabled faculty members to identify malpractices during learning and, later, in examinations, as it detected both copying and plagiarism.

“The importance of artificial intelligence in education was declared by UNESCO in 2019,” said the lead researcher, Laia Sobierates, a lecturer in the College of Computer Science, Multimedia and Telecommunications at the University of Oklahoma, and a research consultant in the ADaS Lab group at UOC’s eHealth Center. and researcher at Eurecat. “In this study, we show that it can be used to prevent malpractice when studying and to identify unusual findings that may mask misconduct, such as plagiarism.”

The study is based on an analysis of trainings conducted by 396 students in an applied computer science undergraduate degree course in a chemical engineering program at the Autonomous University of Madrid using the adaptive learning tool e-valUAM. This e-learning platform offers quizzes with questions that differ depending on whether the answers given are correct or not.

Based on the results of these tests, the research has shown that AI can be used to help students better plan their study methods. “Artificial intelligence can assist continuous learning in different ways,” Sobierats explained. “In addition to spotting bad study strategies and bad practices, it can also customize the pace of learning, provide personalized feedback through smart tutors, and answer questions via educational chatbots.”

Three learning profiles

In analyzing the data, the students were categorized into three groups according to how they studied and the results they achieved: those who work constantly, those who leave it to the last minute, and those who generally get poor results. The continuous study group had the best results. As a result, the study authors argue that strategies to encourage the practice should be sought.

During the lockdown, among other things, face-to-face classes were replaced and more activities were assigned to teachers to do at home, which encouraged students to work continuously. The researchers noted that alternative mechanisms must now be sought to maintain the more consistent working style that was adopted during the months when students were unable to leave their homes.

According to Laia Subirats, there are many tools to help students study continuously, such as providing educational resources, continuous feedback, collaborative learning, and the game. “Some examples that encourage continuous study are setting study goals and routines, learning collaboratively through interaction with teacher and peers, doing hands-on exercises or similar, writing information in students’ own words, studying aloud, and applying mnemonic techniques,” he explains.

Getting students to use these strategies and assisting them with tools like artificial intelligence is the goal put forward by this study to encourage more consistent work and, as a result, better performance.