In recent decades, the use of technological resources such as the eye tracking methodology is providing cognitive researchers with important tools to better understand the learning process. However, the interpretation of the metrics requires the use of supervised and unsupervised learning techniques. The main goal of this study was to analyse the results obtained with the eye tracking methodology by applying statistical tests and supervised and unsupervised machine learning techniques, and to contrast the effectiveness of each one. The parameters of fixations, saccades, blinks and scan path, and the results in a puzzle task were found. The statistical study concluded that no significant differences were found between participants in solving the crossword puzzle task; significant differences were only detected in the parameters saccade amplitude minimum and saccade velocity minimum. On the other hand, this study, with supervised machine learning techniques, provided possible features for analysis, some of them different from those used in the statistical study. Regarding the clustering techniques, a good fit was found between the algorithms used (k-means ++, fuzzy k-means and DBSCAN). These algorithms provided the learning profile of the participants in three types (students over 50 years old; and students and teachers under 50 years of age). Therefore, the use of both types of data analysis is considered complementary.

Teaching in higher education in the 21st century is moving towards e-Learning or b-Learning teaching models. This situation has increased due to the SARS CoV-2 health crisis. Therefore, teaching–learning models must be based on the use of active methodologies that facilitate students’ motivation to work in learning management systems (LMS). One of the most current resources is the digital game-based learning (DGBL) use, specifically in health sciences degrees (e.g., nursing). In this study, we worked with 225 third-year students of degrees in nursing (ND) and occupational therapy (OTD). The objectives were (1) to find out if there were significant differences between students who had worked with DGBL techniques vs. those who had not, and (2) to find out if there were significant differences depending on the type of degree (ND vs. OTD) regarding access to the LMS, learning outcomes and students’ satisfaction with teachers’ performance. A mixed-method research approach was applied. In the quantitative study, significant differences were found in the accesses to the LMS in favor of the groups that had worked with DGBL techniques. Significant differences were also found in ND students with respect to learning outcomes in the group that worked with DGBL. Regarding the results of the qualitative study, differences were found in the frequency of interaction and in the preference of DGBL activities depending on the type of degree. Further studies will investigate the possible causes of these differences.

This study of the use of metacognitive strategies during learning interaction in collaborative groups is considered referential for understanding the development of such strategies. The use of metacognitive strategies is related to better learning outcomes. We monitored the interaction in five collaborative groups at three points in time (initial, intermediate and final). These groups consisted of undergraduate health science (n = 9) and biomedical engineering students (n = 10). The aims were the following: (1) To check whether there were significant differences in the use of metacognitive strategies between the groups of students monitored depending on the type of degree or the point in time measurement. (2) To test whether there were significant differences in students’ learning outcomes depending on whether or not they had participated in the interaction monitoring during collaborative interaction. (3) To test clustering without a pre-assignment variable against learning outcomes in collaborative groups. Significant differences were detected in the use of some of the metacognitive strategies of orientation, planning and elaboration in favor of the collaborative groups of the biomedical engineering students. Also, students who participated in monitoring collaborative groups in both clusters obtained better learning outcomes. Lastly, the assignment groups were exactly related to the collaboration groups with respect to the use of metacognitive strategies in the final measurement.