The researchers highlighted the importance of supporting students foto: Wes Hicks / unsplash.com)
A pilot study with 552 students shows that the technology, which uses artificial intelligence, can also reduce drop-out rates
The system predicts whether a student is going to have problems passing a course with a level of precision ranging from 60% at the start of the academic year to 90% halfway through the semester
The use of technologies based on artificial intelligence is one of the most promising areas for the growth of online teaching and learning. A transdisciplinary research team from the Universitat Oberta de Catalunya (UOC) has developed an adaptive system, the Learning Intelligent System (LIS), which includes an early-warning function to alert teaching staff and students to the risk of failing a course. The LIS is designed to enhance students' performance, providing suitable feedback to guide students on their academic pathways and thus reduce drop-out rates. This system has been implemented in a pilot study with 552 first-year students on two courses of the UOC's Faculty of Economics and Business. The results show that the performance of students who used this technology was better than that of their classmates, and in comparison with earlier semesters. It also helped increase student engagement during the semester, significantly reducing drop-out rates.
"These results are particularly significant as these are key, compulsory courses for students enrolled on this degree. Furthermore, for many students this is likely to be their first experience of online learning and the LIS system improved their commitment to learning, increased their motivation and helped them to be more self-sufficient and work more effectively," explained Ana Elena Guerrero, lead researcher of the Technology Enhanced Knowledge and Interaction Group (TEKING) in the UOC's Faculty of Computer Science, Multimedia and Telecommunications. She is also lead author of the article published in the International Journal of Educational Technology in Higher Education (ETHE), which is coedited by the UOC and one of the world's most leading journals in the field of education and technology.
The paper was also authored by M. Elena Rodríguez-González, member of TEKING and the Faculty of Computer Science, Multimedia and Telecommunications; David Bañeres from the Systems, Software and Models Research Lab group (SOM Research Lab) in the Internet Interdisciplinary Institute (IN3), and Pau Cortadas, Innovative tools for elearning (GO2SIM) researcher, and Amal Elasri-Ejjaberi, from the Faculty of Economics and Business.
A system that predicts the risk of failure
The LIS project began in February 2019 under the New Goals call for research proposals organized by the eLearn Center with the aim of developing projects that could apply artificial intelligence to the UOC's Virtual Campus. The system works by processing all the information collected in the data mart, an institutional database developed six years ago by the UOC, which contains historical and current data on students' academic progress. The system stores anonymized data including details of students' online behaviour during assessed activities, their level of engagement (i.e. browsing history, use of resources and tools) and their academic marks.
The LIS uses these data, combined with algorithms based on artificial intelligence techniques, to perform a predictive analysis of students' progress. The model allows the system to predict whether a student is going to have problems passing a course with a level of precision ranging from 60% at the start of the academic year, when there is little information available about them, to almost 90% halfway through the semester, as borne out by earlier studies carried out by the same research team.
Messages of support with personalized information
After assessing each learning activity, the system calculates the probability that the student will pass the course and advises teaching staff and the student using a traffic light system (green, amber, red). Students also receive a personalized email with tips on how to improve, and recommendations such as contacting teaching staff to clear up doubts or reviewing earlier content to prepare for the next activity.
These messages can be triggered automatically or by teaching staff, and they vary according to the risk level the student is classified under. "One of the distinctive features of this system is that all students, including those most at risk of failing (red) and those least at risk (green), receive messages tailored to their situation," said Guerrero.
To assess what impact these messages had on academic outcomes for the course, the researchers compared the results of the group that used the LIS system with those of the students who did the same course with the UOC's usual communication mechanisms, and with those of a third group consisting of the students enrolled in the previous semester, before the new technology was introduced. "The group that used the LIS system outperformed the other two groups, demonstrating that this type of feedback, combined with the student's Virtual Campus panel, had a positive impact, complementing the normal feedback mechanisms used for courses," said Guerrero.
The researchers highlighted the importance of supporting students, especially in the case of online learning. "We know that students are more likely to drop out of a course when they feel demotivated, unsure whether they will pass it, or overwhelmed by the work and the competencies they have to acquire. This is especially so for online environments, where isolation and a lack of information are among the main factors leading students to drop out. These messages are vital for motivating students and supporting them throughout the learning process," they said.
A new tool to help teaching staff
From a teaching perspective, the researchers pointed out that the LIS system is a tool that can help them manage courses more efficiently and provide better support to students: "The system provides information about students' progress and gives teaching staff more opportunities to engage in the learning process and provide guidance. The system also provides information about the student right from the start of the course, so these decisions no longer have to be based purely on teachers' professional experience."
A useful, effective resource for students
At the end of the semester, the researchers surveyed the students who took part in the pilot to find out their views on the effectiveness of the system and its usefulness. The results show that most participants believe that the LIS system provides "effective support and helped them to pass the course". 68.29% said they would be willing to continue using the system in future semesters as they found it beneficial.
This research by the UOC promotes Sustainable Development Goal (SDG) 4, Quality Education.
Guerrero-Roldán, A. E., Rodríguez-González, M. E., Bañeres, D. et al. Experiences in the use of an adaptive intelligent system to enhance online learners' performance: a case study in Economics and Business courses. Int J Educ Technol High Educ 18, 36 (2021). https://doi.org/10.1186/s41239-021-00271-0
Bañeres, D.; Rodríguez, M. E.; Guerrero-Roldán, A. E.; Karadeniz, A. (2020). An Early Warning System to Detect At-Risk Students in Online Higher Education. Applied Sciences. 2020, 10(13), 4427; https://doi.org/10.3390/app10134427
The UOC's research and innovation (R&I) is helping overcome pressing challenges faced by global societies in the 21st century, by studying interactions between technology and human & social sciences with a specific focus on the network society, e-learning and e-health.
The United Nations' 2030 Agenda for Sustainable Development and open knowledge serve as strategic pillars for the UOC's teaching, research and innovation. More information: research.uoc.edu #UOC25years
Ana Elena Guerrero Roldán
Expert in: Design, creation and analysis of ICT tools and resources for improving e-assessment processes, to encourage personalization and formative adaptation through the creation of adaptive pathways for online teaching and learning processes.
Knowledge area: Technology Enhanced Learning (TEL), aprenentatge en línia, e-assessment, educació i TIC.
Maria Elena Rodríguez
SOM Research Lab researcher
Researcher at the Faculty of Economics and Business