Increased performance in tutoring systems during COVID-19 in Uruguay and Germany.

BACKGROUND

COVID-19-related school closures globally disrupted students' education and were followed by declines in academic performance in many contexts. At the same time, some studies reported performance increases within adaptive learning software during school closures. Yet, this evidence stems from a limited range of countries (e.g., Germany), leaving unclear whether these findings extend to other parts of the world.

AIM: We sought to evaluate whether performance trajectories within intelligent tutoring systems (ITSs) for learning mathematics during COVID-19-related school closures were similar for students from Germany and from Uruguay-a country and cultural context that has not yet received systematic attention in this line of research.

SAMPLES: We conducted within-student analyses of two longitudinal ITS datasets from Uruguay (1357 students; 42,404 problem sets) and Germany (8751 students; 298,300 problem sets) and complemented these with two between-student cohort analyses (Uruguay: 9618 students; 287,573 problem sets; Germany: 48,923 students; 1,435,234 problem sets).

METHODS

We applied hierarchical linear regression models to compare students' performance within the ITS before and during COVID-19-related school closures in mathematics in both countries.

RESULTS

We observed significantly better performance within the ITS during periods of COVID-19-related school closures than during the same period in previous years in both countries and in both the within-student and the between-student cohort analyses. Greater system use was associated with better performance within the ITS, and students who increased their system use during COVID-19-related school closures relative to before also showed larger performance improvements within the ITS.

CONCLUSIONS

Our results indicate that previously reported performance increases within ITSs for learning mathematics during periods of COVID-19-related school closures also pertain to students from Uruguay and highlight the need to diversify research samples. Our findings further indicate that associations between system use and performance within the ITS during school closures are not restricted to Germany.