A multilayer inference engine for individualized tutoring model: adapting learning material and its granularity

Abstract

Computer-supported approaches have been widely used for enriching the learning process. The technological advances have led tutoring systems to embody intelligence in their functionalities. However, so far, they fail to adequately incorporate intelligence and adaptivity in their diagnostic and reasoning mechanisms. In view of the above, this paper presents a novel expert system for the instruction of the programming language Java. A multilayer inference engine was developed and used in this system to provide individualized instruction to students according to their needs and preferences. The multilayer inference engine incorporates a set of algorithmic methods in different layers promoting personalization in the tutoring strategies. In particular, an artificial neural network and multi-criteria decision analysis are used in one layer for adapting the learning units based on students’ learning style, and a fuzzy logic model is applied in the other layer for defining the granularity of learning units according to students’ profile characteristics, such as learning style, knowledge level and misconceptions. The students’ learning style is based on the Honey and Mumford model. The evaluation of the system was conducted using an established framework and Student’s t test, and the results showed a high level of acceptance of the presented model.