This article is a logical continuation of the material published in the journal “Informatics and Education” № 6-2018. The authors consider the issues of predicting learning outcomes based on the calculation of negentropy, which is proposed to be considered as an integral information indicator characterizing the quality of student learning.
The work can be divided into three stages and is based on ... [Show full abstract] the construction of the hierarchical structure of the criteria-based quality system. At the first stage, a questionnaire was developed for the survey of expert teachers, in which it was necessary to note, from the point of view of importance, the criteria of the first and second levels those influence the process of emergent learning. At the second stage, using an expert rationing method, an array of expert estimates was processed, representing an example of a fuzzy set. As a result, weighting coefficients were obtained according to the criteria of the first and second levels. At the third stage, a dichotomous assessment of the third level criteria was carried out and the integrated values of negentropy were calculated for the three directions of training and for the model situation.
The algorithms proposed in the article can be used both to assess the quality of already developed online courses, products or educational processes with their use, and to predict learning outcomes based on expert assessment.