FEATURE-BASED MODELING - A METHODOLOGY FOR PRODUCING COHERENT, CONSISTENT, DYNAMICALLY CHANGING MODELS OF AGENTS COMPETENCES

Feature Based Modelling uses attribute value machine learning techniqu es to model an agent's competency. This is achieved by creating a mode l describing the relationships between the features of the agent's act ions and of the contexts in which those actions are performed. This pa per describes techniques that have been developed for creating these m odels and for extracting key information therefrom. An overview is pro vided of previous studies that have evaluated the application of Featu re Based Modelling in a number of educational contexts including piano keyboard playing, the unification of Prolog terms and elementary subt raction. These studies have demonstrated that the approach is applicab le to a wide spectrum of domains. Classroom use has demonstrated the l ow computational overheads of the technique. A new study of the applic ation of the approach to modelling elementary subtraction skills is pr esented. The approach demonstrates accuracy in excess of 90% when pred icting student solutions. It also demonstrates the ability to identify and model student's buggy arithmetic procedures.