Artificial intelligence can identify students who need extra help

A pilot study of the use of artificial intelligence to detect the needs of students in remote learning has concluded that the data obtained can be used by teachers to offer help to the students who most need it. The research, carried out in conjunction with the Universitat Oberta de Catalunya (UOC), the Eurecat technological center and the Universidad Autónoma de Madrid, will help solve one of the biggest problems faced by off-site education, which has become more widespread during the pandemic: how to obtain information concerning the progress of students in order to provide them with the necessary support before it is too late. Laia Subirats, a course instructor at the UOC's Faculty of Computer Science, Multimedia and Telecommunications and a researcher at Eurecat, said: "We were able to carry out a continuous assessment in pre-pandemic years, then during lockdown and later in the second wave of the pandemic." She added: "Our objective is to develop a method to improve remote learning which will allow teachers to identify students who are at risk of failing, so that they, as well as the students themselves, can reinforce their learning process." The study, published in the open-access scientific journal Applied Sciences, drew on information gathered from 396 university students between the 2016/2017 and 2020/2021 academic years. Before the final exam, students were given the chance to take tests featuring various questions adapted to their individual level.