Expert software agent for the diagnosis of possible dyslexia

Abstract

Since the beginning of recorded history, people have been fascinated with the idea of non-human agencies. Popular notions about androids, humanoids, robots and cyborgs creatures permeate our culture, forming the unconscious backdrop against which software agents are perceived. As in the everday sense, we expect a software agent to act on behalf of someone to carry out a particular task which has been delegated to it. The best agents would not only need to exercise a particular form of expertise, but also take into account the peculiarties of the user and situation. Our fundamental aim in writing this article is to provide a general and clear definition of dyslexia as a concept and as a group of symptoms. In the article, we also aim at highlighting the major areas the examination of which could serve as a basis of designing an expert software agent that analyses possibility to dyslexia. During the development of such an expert agent, we had to pay special attention to the fact that the probable future users of the system would not necessarily be information technology experts, but instructors and others dealing with the targeted age group, i.e. first grade students in elementary school. Another challenge during system development was to find different areas where susceptibility to dyslexia could be examined, areas for the examination of which the active participation of children was not necessary. The test under different headings can be answered simply by monitoring the everyday behaviour and habits of the child. During expert software agent evaluation, attention might be called to any possible orientation, visual-motor-coordination, motor-coordination, concentration or memory disorders, inadequately developed general abilities, delayed development of speech or a bad reading technique.