Background: Deep learning methods, where models do not use explicit features and instead rely on implicit features estimated during model training, suffer from an explainability problem. In text classification, saliency maps that reflect the importance of words in prediction are one approach toward explainability. However, little is known about…

Background: In example-based learning, examples are often combined with generative activities, such as comparative self-explanations of example cases. Comparisons induce heavy demands on working memory, especially in complex domains. Hence, only stronger learners may benefit from comparative self-explanations. While static text-based examples can…

This article develops a framework for self-regulated digital learning, which supports for self-regulated learning (SRL) in e-learning systems. The framework emphasizes 8 features: learning plan, records/e-portfolio and sharing, evaluation, human feedback, machine feedback, visualization of goals/procedures/concepts, scaffolding, and agents. Each…

The issues raised by the design and development of technologies to enhance learning has led to a demand for an appropriate language and form of conceptualization. However, we are insufficiently familiar with the way in which different types of mediated tool use occur, to develop the theoretical models needed for the development of this language…

Described is how an iconic model building software can be used to help students gain a deeper qualitative conceptual understanding of physics concepts. The program, STELLA, links research about misconceptions and new teaching strategies with the use of modern information technology tools. (31 references) (KR)

Examines the place of mental models in the process of knowledge construction, particularly by the relationship between mental models and computer models in that process. Analyzes and discusses children's use of spreadsheets to build their own computer models. Suggests that the process of building models on a computer may provide direct support to…

Reports on a one-year action research study at the University of Cambridge (United Kingdom) which explored processes by which a cohort of postgraduate teacher trainees learned personal information and communication technology (ICT) skills. Discusses learning strategies reported by students in interviews; considers previous experience and software…

Describes the Vicarious Learner Project, a project which investigates the fundamental role of dialog for learning, specifically the benefits to learners of being able to observe others participating in discussion. Theoretical aspects of the work, a high-level process model of learning, and a more detailed logic model of what happens in educational…