Initializing the student model using stereotypes and machine learning
Victoria Tsiriga, Maria K. Virvou · 2005
In this paper we describe the method for initializing the student model in a Web-based Algebra Tutor, which is called Web-EasyMath. The system uses an innovative combination of stereotypes and the distance weighted k-nearest neighbor algorithm to initialize the model of a new student. In particular, the student is first assigned to a stereotype category concerning her/his knowledge level based on her/his performance on a preliminary test. The system then initializes all aspects of the student model using the distance weighted k-nearest neighbor algorithm among the students that belong to the same stereotype category with the new student. The basic idea of the application of the algorithm is to weigh the contribution of each of the neighbor students according to their distance from the new student; the distance between students is calculated based on a similarity measure. In the case of Web-EasyMath the similarity measure is estimated taking into account the school class students belong to, their degree of carefulness while solving exercises as well as their proficiency in using simple arithmetic operations.