Prilagodljivi računalniški sistem za priporočanje učnih objektov v konstruktivističnem učnem okolju – ALECA

Today there are increasingly more learning environments which support active learning, taking into account student characteristics, preferences and activities. In this paper, we present a concept of a learning recommender system, which combines knowledge from pedagogy and recommending systems. We analyse the influence of combining different learning styles models on preferred types of multimedia materials. The results reveal that students prefer well-structured learning texts with color discrimination, and that the hemispheric learning style model is the most important criterion in determining student preferences for different multimedia learning materials. In the second part of our research, we describe an approach to alleviating the new user problem in terms of better recommendation accuracy of the system for recommending learning materials in environments where the system has no prior information about learners. Our findings present the concept of an adaptive learning system, with an analysis of its possible effects in learning practice