Stefan Weinbrenner

Ontology-supported scaffolding of concept maps

Concept maps are often used in inquiry learning as tools for conceptual modelling, but also as a means to externalise and diagnose conceptual understanding. The latter use is closely related to intelligent feedback and scaffolding. Previous approaches used an expert concept map as a reference to generate intelligent feedback. This paper describes an approach that takes a domain ontology as its only input.

Supporting Cognitive Competence Development in Virtual Classrooms - Personal Learning Management and Evaluation Using Pedagogical Agents

Self-directed learning with learning management systems can be intelligently supported and enriched using available log data in combination with detailed competence ontologies. The approach described here implements a mechanism to adaptively generate quizzes for self-assessment in a Moodle environment. The underlying agent architecture uses a tuple space in the role of a blackboard. The approach has been worked out with a distance course on Genetics.

Una arquitectura flexible orientada hacia el agente para análisis de interacción y retroalimentación.

An architectural framework for the engineering of distributed learning environments is described, which allows for plugging in intelligent support agents programmed in multiple languages agent. The framework implements a blackboard architecture with a Java-based central Tuple Space server and clients that differ in hardware (PDAs, PCs with projection) and possibly in programming languages (C#, Prolog, Java). On this basis, it is possible to analyze and flexibly support learning activities based on action logs as well as system state information. This framework has been used for supporting group discussions including design meetings with mobile input devices and a large public display. Analytic agents have been implemented in Prolog.