A trial study was conducted on the usage of artificial intelligence to find out what students pursuing remote learning really needed. The study has concluded that the information obtained by AI could be utilized by teachers to provide help to the students who need it the most.
Students were given the chance to take tests featuring various questions adapted to their individual level. Image Credit: Christin Hume/unsplash.com.
The study — conducted jointly with the Universitat Oberta de Catalunya (UOC), the Eurecat technological center, and the Universidad Autónoma de Madrid — will aid in solving one of the toughest challenges faced by remote education that has become more common in the pandemic: how to acquire data regarding the students’ progress to give them the support they need before it is too late.
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. 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.
Laia Subirats, Course Instructor, Faculty of Computer Science, Multimedia and Telecommunications, Universitat Oberta de Catalunya
Subirats is also a researcher at the Eurecat and works with the Applied Data Science Lab (ADaS).
The study drew on the data collected from 396 university students between the academic years of 2016/2017 and 2020/2021. Students were offered the option to take tests that have different questions modified to the individual’s level before the final exam. From the results, students were categorized as excellent, on track or at risk.
One of the challenges was detecting poor-performing students in cases where they crammed at the last minute because the system was unable to predict this early enough. But it is easy to spot students who fall in the excellent category since those who study in a more ongoing manner obtain better results.
Laia Subirats, Course Instructor, Faculty of Computer Science, Multimedia and Telecommunications, Universitat Oberta de Catalunya
Technology for Improving Assessment
One of the biggest difficulties faced by off-site education is the requirement for advanced technology in the learning process and, specifically, in testing student performance. The COVID-19 pandemic, which compelled schools to stop face-to-face classes, has only helped in underlining this fact. Nevertheless, digital tools, like online assessment platforms, provide novel opportunities with respect to remote learning.
These sorts of tools also serve to break down many barriers and can help democratize knowledge. The fact that you can study anywhere and at the time that suits you best greatly favors those who are unable to follow a more conventional way of learning.
Laia Subirats, Course Instructor, Faculty of Computer Science, Multimedia and Telecommunications, Universitat Oberta de Catalunya
Moreover, AI and its forecasts could also aid in finding potential plagiarism or fraud. “If a student obtains a much higher grade than what our system predicted, that could be a cause for suspicion,” concludes the researcher.
Journal Reference:
Subirats, L., et al. (2021) Artificial Intelligence to Counterweight the Effect of COVID-19 on Learning in a Sustainable Environment. Applied Science. doi.org/10.3390/app11219923.