Tomasz D. Loboda

Bayesian networks for student model engineering

Bayesian networks are graphical modeling tools that have been proven very powerful in a variety of application contexts. The purpose of this paper is to provide education practitioners with the background and examples needed to understand Bayesian networks and use them to design and implement student models. The student model is the key component of any adaptive tutoring system, as it stores all the information about the student (for example, knowledge, interest, learning styles, etc.) so the tutoring system can use this information to provide personalized instruction. Basic and advanced concepts and techniques are introduced and applied in the context of typical student modeling problems. A repertoire of models of varying complexity is discussed. To illustrate the proposed methodology a Bayesian Student Model for the Simplex algorithm is developed.

Mastery grids: an open-source social educational progress visualization

Many pieces of educational software are underused by students. Open learning model and social visualization are two approaches which have been helpful in ameliorating that low usage problem. This article introduces a fusion of these two ideas in a form of social progress visualization. A classroom evaluation indicates that this combination may be effective in engaging students, guiding them to suitable content, and enabling faster content access.

Inferring word relevance from eye-movements of readers

Reading is one of the most important skills in todays society. The ubiquity of this activity has naturally affected many information systems; the only goal of some is the presentation of textual information. One concrete task often performed on a computer and involving reading is finding relevant parts of text. In the current study, we investigated if word-level relevance, defined as a binary measure of an individual word being congruent with the readers current informational needs, could be inferred given only the text and eye movements of readers. We found that the number of fixations, first-pass fixations, and the total viewing time can be used to predict the relevance of sentence-terminal words. In light of what is known about eye movements of readers, knowing which sentence-terminal words are relevant can help in an unobtrusive identification of relevant sentences.

WADEIn II: a case for adaptive explanatory visualization

Adaptive explanatory visualization is an attempt to integrate two promising approaches to program visualization: adaptive visualization and explanatory visualization. The goal of this paper is to demonstrate the ideas of adaptive explanatory visualization using a practical example. The paper introduces the WADEIn II system for the visualization of expression evaluation in the C programming language, shows how expression evaluation visualizations can be made adaptive, and explains our approach to the adaptive generation of explanations.

User-adaptive explanatory program visualization: evaluation and insights from eye movements

User-adaptive visualization and explanatory visualization have been suggested to increase educational effectiveness of program visualization. This paper presents an attempt to assess the value of these two approaches. The results of a controlled experiment indicate that explanatory visualization allows students to substantially increase the understanding of a new programming topic. Furthermore, an educational application that features explanatory visualization and employs a user model to track users’ progress allows students to interact with a larger amount of material than an application which does not follow users’ activity. However, no support for the difference in short-term knowledge gain between the two applications is found. Nevertheless, students admit that they prefer the version that estimates and visualizes their progress and adapts the learning content to their level of understanding. They also use the application’s estimation to pace their work. The differences in eye movement patterns between the applications employing adaptive and non-adaptive explanatory visualizations are investigated as well. Gaze-based measures show that adaptive visualization captivates attention more than its non-personalized counterpart and is more interesting to students. Natural language explanations also accumulate a big portion of students’ attention. Furthermore, the results indicate that working memory span can mediate the perception of adaptation. It is possible that user-adaptation in an educational context provides a different service to people with different mental processing capabilities.

Mastery Grids: An Open Source Social Educational Progress Visualization

While many pieces of educational software used in the classroom have been found to positively affect learning, they often are underused by students. Open learning model and social visualization are two approaches which have been helpful in ameliorating that low usage problem. This article introduces a fusion of these two ideas in a form of social progress visualization. A classroom evaluation indicates that this combination may be effective in engaging students, guiding them to suitable content, and enabling faster content access.

Distributed Framework for Adaptive Explanatory Visualization

Educational tools designed to help students understand programming paradigms and learn programming languages are an important component of many academic curricula. This paper presents the architecture of a distributed event-based visualization system. We describe specialized content provision and visualization services and present two communication protocols in an attempt to explore the possibility of a standardized language.

WADEIn II: adaptive explanatory visualization for expressions evaluation

Adaptive visualization and explanatory visualization have been suggested as two approaches to increasing the educational effectiveness of software visualization. This paper presents our work on the integration of adaptive and explanatory visualization. We introduce the motivation behind this research and describe how adaptive, explanatory visualization is implemented in WADEIn II, a system that visualizes the process of expression evaluation in the C programming language.