Jože Rugelj

Exploring the relation between learning style models and preferred multimedia types

There are many adaptive learning systems that adapt learning materials to student properties, preferences, and activities. This study is focused on designing such a learning system by relating combinations of different learning styles to preferred types of multimedia materials. We explore a decision model aimed at proposing learning material of an appropriate multimedia type. This study includes 272 student participants. The resulting decision model shows that students prefer well-structured learning texts with color discrimination, and that the hemispheric learning style model is the most important criterion in deciding student preferences for different multimedia learning materials. To provide a more accurate and reliable model for recommending different multimedia types more learning style models must be combined. Kolbs classification and the VAK classification allow us to learn if students prefer an active role in the learning process, and what multimedia type they prefer.

Improving matrix factorization recommendations for examples in cold start

Novel framework for the imputation of missing values into the ratings matrix.Imputation of missing values significantly reduces matrix factorization prediction error.Increased matrix factorization performance in the cold start state. Recommender systems suggest items of interest to users based on their preferences (i.e. previous ratings). If there are no ratings for a certain user or item, it is said that there is a problem of a cold start, which leads to unreliable recommendations. We propose a novel approach for alleviating the cold start problem by imputing missing values into the input matrix. Our approach combines local learning, attribute selection, and value aggregation into a single approach; it was evaluated on three datasets and using four matrix factorization algorithms. The results showed that the imputation of missing values significantly reduces the recommendation error. Two tested methods, denoted with 25-FR-ME-? and 10-FR-ME-?, significantly improved performance of all tested matrix factorization algorithms, without the requirement to use a different recommendation algorithm for the users in the cold start state.

Learning programming with serious games

Students who are learning to program often have difficulties understanding cognitively complex concepts. Teaching programming is mainly focused on the syntax and features of programs, rather than to a deeper understanding of programming constructs and abstract concepts. Computer game stimulates active learning and presentation of learning content in a variety of contexts that are funny and engaging for students. This has a positive impact on the motivation to learn. This paper deals mainly with defining the programming knowledge and common problems with teaching programming, comparing the properties of novice and experts programmers and introducing the semantic method of teaching programming where one would teach only the semantics of programming constructs unbound to specific programming language in an interactive motivating setting of educational computer game. In this paper we discuss the main characteristics of computer games and specific features which makes them useful in the educational setting. As an example of presented method we introduce a game on the presentation of variables in programming. The game is based on visualizations of different types of variables and on the interpretation of the assignment sentence. The game actively encourages interactivity and deeper learning.

Constructivist Learning Environment in a Cloud

The paper presents a development of web-based learning environment for constructivist learning in higher education. The main focus in the design was to take into account recent findings of pedagogical research and availability of new technologies in order to create efficient and effective learning support for the engineering students. The central component of the environment is a virtual laboratory, which is defined as a service that can be used in a cloud – LaaS (Laboratory as a Service). The paper also presents our experience with the environment used in Computer Science classes with over 700 students who experienced active forms of learning, collaboration and appropriate feedback.

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.

Serious Computer Games Design for Active Learning in Teacher Education

Active learning is a pedagogical method that focuses the responsibility of learning on learners. They engage in activities, such as reading, writing, discussion, or problem solving that promote analysis, synthesis, and evaluation of class content. Cooperative learning, problem-based learning, and the use of case methods and simulations are some approaches that promote active learning. Serious games design can provide a framework to support confirmation, structured, and guided inquiry. There is a convergence between the core elements of a good serious game design and the characteristics of productive learning. Another link between games and learning is formative feedback as a critical part of any learning effort and a key component in game design that adjusts challenges.

Designing an Interactive Teaching Tool with ABML Knowledge Refinement Loop

Argument-based machine learning (ABML) knowledge refinement loop offers a powerful knowledge elicitation tool, suitable for obtaining expert knowledge in difficult domains. In this paper, we first use it to conceptualize a difficult, even ill-defined concept: distinguishing between “basic” and “advanced” programming style in python programming language, and then to teach this concept in an interactive learning session between a student and the computer. We demonstrate that by automatically selecting relevant examples and counter examples to be explained by the student, the ABML knowledge refinement loop provides a valuable interactive teaching tool.