The process of associating elements of learning content with concepts or skills that this content helps students to master is one of the critical steps in developing personalized educational systems. When these associations are properly established, the system can infer the growth of student understanding of separate knowledge components from the logs of their interactions with associated learning content and use it to adapt the learning process accordingly by targeting gaps in individual students’ knowledge. Unfortunately, crafting these links between learning content and knowledge components is a very time- and expertise-demanding process that has traditionally been performed manually by domain experts with the help of knowledge engineers. Recently, the power of Large Language Models has motivated a new generation of research on concept extraction from textual learning content. The work presented in this paper contributes to this trend while introducing two important innovations. First, our concept extraction process is guided by a human-authored ontology of the target domain - Python programming. Second, alongside a traditional expert evaluation of the concept extraction quality, we apply two additional validation approaches: one based on using an educational data mining technique (learning curves) and another utilizing the pedagogical expertise of teaching the target domain (learning content placement).

Education technology often incorporates social comparison (SC) features such as leaderboards, social progress indicators, and comparative performance graphs to support students' motivation and engagement. Yet students' reactions to SC, and hence its impact on their behavior, can vary substantially. Recent research reports mixed effects of SC in learning, suggesting that individual motivational dispositions may moderate its effects. This observation stresses the need for more personalized approaches towards using SC in educational applications which would require profiling students based on their motivational traits. We introduce a trait-based profiling approach grounded in students' goal orientation, competitiveness, and learning strategies to characterize variability in voluntary engagement with SC. In an observational study conducted in a real-world learning context, we have examined how students with different profiles interact with a one-size-fits-all implementation of SC and how the presence or absence of SC is associated with differences in their engagement and performance. In isolation, the use of SC and the profiles show limited main effects. However, the analysis of the associations between SC and engagement within each profile using Bayesian hierarchical modeling suggests that Competitive students tend to exhibit higher engagement when SC is present, Independent students seem to be less affected, and the students characterized as Vulnerable consistently demonstrate less favorable engagement patterns under SC. These findings highlight the potential value of interpretable, trait-driven student profiles for guiding profile-sensitive personalization of SC in adaptive learning interfaces.

A typical index at the end of a textbook contains a manually-provided vocabulary of terms related to the content of the textbook. In this paper, we extend our previous work on extraction of knowledge models from digital textbooks. We are taking a more critical look at the content of a textbook index and present a mechanism for classifying index terms according to their domain specificity: a core domain concept, an in-domain concept, a concept from a related domain, and a concept from a foreign domain. We link the extracted models to DBpedia and leverage the aggregated linguistic and structural information from textbooks and DBpedia to construct and prune the domain-specific knowledge graphs. The evaluation experiments demonstrate (1) the ability of the approach to identify (with high accuracy) different levels of domain specificity for automatically extracted concepts, (2) its cross-domain robustness, and (3) the added value of the domain specificity information. These results clearly indicate the improved quality of the refined knowledge graphs and widen their potential applicability.

Textbooks are educational documents created, structured and formatted by domain experts with the main purpose to explain the knowledge in the domain to a novice. Authors use their understanding of the domain when structuring and formatting the content of a textbook to facilitate this explanation. As a result, the formatting and structural elements of textbooks carry the elements of domain knowledge implicitly encoded by their authors. Our paper presents an extendable approach towards automated extraction of this knowledge from textbooks taking into account their formatting rules and internal structure. We focus on PDF as the most common textbook representation format; however, the overall method is applicable to other formats as well. The evaluation experiments examine the accuracy of the approach, as well as the pragmatic quality of the obtained knowledge models using one of their possible applications -- semantic linking of textbooks in the same domain. The results indicate high accuracy of model construction on symbolic, syntactic and structural levels across textbooks and domains, and demonstrate the added value of the extracted models on the semantic level.

Training children safe behavior in traffic situations is both important and challenging. One of the problems is children’s limited perceptual-motor abilities and associated difficulties with important cognitive skills required to be safe pedestrians. Existing traffic education programs focus more on theoretical knowledge, while training practical skills in the real world is dangerous, expensive and hard to organize. This paper presents a promising alternative – an intelligent virtual reality training environment that allows children to practice their pedestrian skills. It describes the interface and architecture of the system, as well as the skill model of the pedestrian safety domain. The results of the conducted pilot study show that children of the target age group rarely have problems with applying (and acquiring) “basic” pedestrian skills in the developed virtual environment. However, when applying and learning “advanced” skills, they require additional support.

Quality of learning objects metadata, in many respects, defines the quality of an adaptive learning environment presenting these learning objects to a student. Metadata inconsistencies and gaps may be the cause of various problems: from a system malfunction to ineffective learning experiences. In this paper, we propose an intelligent and rigorous mechanism for detecting metadata gaps in collections of learning content. The mechanism converts learning objects metadata into an OWL2 ontology, detects logical conflicts using Semantic Web reasoning techniques and generates human-readable explanations for an author to resolve the gaps. The evaluation of the developed semantic gap detection tool with real learning content collections demonstrates its effectiveness.

This paper describes the development and evaluation of a Bayesian network model of student misconceptions in the domain of decimals. The Bayesian model supports a remote adaptation service for an intelligent t utoring system within a project focused on adaptively presenting erroneous examples to students. We have evaluated the accuracy of the student model by comparing its predictions to the outcomes of the interactions of 255 students with the software. Student s’ logs were used for retrospective training of the Bayesian network parameters. The accuracy of the student model was evaluated from three different perspectives: its ability to predict the outcome of an individual student’s answer, the correctness of the answer, and the presence of a particular misconception. The results show that the model is capable of producing predictions of high accuracy (up to 87%).

Rich, interactive eLearning tools receive a lot of attention nowadays from both practitioners and researchers. However, broader dissemination of these tools is hindered by the technical difficulties of their integration into existing platforms. This article explores the technical and conceptual problems of using several interactive educational tools in the context of a single course. It presents an integrated Exploratorium for database courses, an experimental platform, which provides personalized access to several types of interactive learning activities. Several classroom studies of the Exploratorium have demonstrated its value in both the integration of several tools and the provision of personalized access.

Problem-tracing questions are popular among teachers of various programming languages. In an assessment mode these questions allows to evaluate student knowledge of language semantics. In a self-assessment mode, they provide an excellent learning tool. A 2004 ITiCSE working group report [4] stressed the importance of this type of questions to build foundation of higher-level knowledge. Yet the use of problem-tracing questions is still limited due to a large authoring overhead. To resolve this bottleneck, we explored the idea of parameterized question generation [2]. We developed QuizPACK [1], a system which can generate parameterized problem-tracing questions for C programming language. We also developed QuizGuide [1], a personalized guidance system for QuizPACK, which models student knowledge and guides students individually to most appropriate questions to try. The results of our studies demonstrated that QuizPACK strongly benefits student knowledge and that QuizGuide personalized guidance technology increased student ability to answer questions correctly and encouraged them to use the system more extensively (which, in turn, positively impacted their knowledge) [1]. However, parameterized questions in area of C programming were not as diverse from the complexity point of view as parameterized questions explored in other areas such as physics [2]. As a result, it was left unclear whether personalized guidance technology can successfully guide students to a broader range of questions from relatively simple to very difficult.The work reported in this poster expands our work on parameterized questions to a more sophisticated domain of object-oriented Java programming, which allowed us to introduce questions of much broader. Capitalizing on our experience with QuizPACK, we developed QuizJET (Java Evaluation Toolkit), which supports authoring, delivery, and evaluation of parameterized questions for Java [3]. We also implemented JavaGuide system (Figure 1), which provides personalized guidance for QuizJET questions. We assessed the impact of adaptive navigation support to student work with questions of different complexity as well as the impact of this technology on weaker and stronger students. The results of two classroom studies indicate that personalized guidance encouraged students to use parameterized questions more extensively and also helped them to access right questions at the right time. Students were 2.5 times more likely to answer a quiz correctly with personalized guidance than without such it. In addition, we found that personalized guidance especially benefited weak students to achieve scores comparable with the scores of strong students on each complexity level of questions.

In this paper, we present an open architecture that combines different SQL learning tools in an integrated Exploratorium for database courses. The integrated Exploratorium provides a unique learning environment that allows database students to take complimentary advantages of multiple advanced learning tools.

We explored two approaches for encouraging introductory programming students to use the web-based, self-assessment system, QuizPACK. An "organizational" approach applied specially constructed classroom quizzes, while the "technical" approach introduced adaptive guidance. Our studies demonstrated that each of these caused a dramatic increase in system use. This approach could be useful in many other contexts, when an educationally beneficial system is underused by students.

Individualized exercises are a promising feature in promoting modern e-learning. The focus of this article is on the QuizPACK system, which is able to generate parameterized exercises for the C language and automatically evaluate the correctness of student answers. We introduce QuizPACK and present the results of its comprehensive classroom evaluation during four consecutive semesters. Our studies demonstrate that when QuizPACK is used for out-of-class self-assessment, it is an exceptional learning tool. The students' work with QuizPACK significantly improved their knowledge of semantics and positively affected higher-level knowledge and skills. The students themselves praised the system highly as a learning tool. We also demonstrated that the use of the system in self-assessment mode can be significantly increased by basing later classroom paper-and-pencil quizzes on QuizPACK questions, motivating students to practice them more.

This paper discusses a need to provide adaptive navigation support for students accessing large numbers of interactive examples in Web-enhanced education. We introduce the system NavEx that is able to provide adaptive annotation of programming examples without any need of manual indexing. NavEx uses innovative algorithms for prerequisite/outcome indexing of learning material and an efficient knowledge-based approach for adaptive annotation.

The paper discusses problems of integrated leaning environment (ILE) creation. An architecture for ILE is suggested. An approach to learning management organization in such environments is described. The paper considers in detail the situations when the student does not achieve enough success in educational problem solving. In these cases, the system sends him/her back to a hypertext textbook to learn theoretical material. The suggested approach is invariant for the broad class of domains. The instrumental tools, MONAP-II ,support this approach.

The elements of intelligent tutoring systems (ITS) design technology for a broad class of domains are described. Characteristic features of the proposed technology are considered. Restrictions on the area of its application are posed. Describing technology has been realized in the authoring tools for ITS design, which are part of the program complex MONAP-II. For a number of domains, MONAP-II provides full automation of ITS design.