Digitalization of the thesaurus approach in education
The article describes what the thesaurus approach in education is like, its origins are justified, and it also suggests the implementation of certain areas of digitalization of the thesaurus approach. The thesaurus approach is illustrated by two tasks: 1) the identification of individual stylistic features of authors’ texts; 2) assessment of learning outcomes (semi-automatic assessment of texts generated by students during the educational process). The first task is illustrated in more details, in it the Kullback— Leibler information measures are used, familiarity with which, in our opinion, will be useful to informatics teachers and readers of the journal. In addition, the calculations made in the first task can be reproduced even by school students in the framework of, for example, project activity. In the second task, the less sensitive Spearman statistical method was used. The thesaurus approach allows using information methods to consider a number of other tasks related to the pedagogical process. In particular, the main direction of work on the thesaurus approach is seen in the search and testing of algorithmic prescriptions for the quantitative/numerical analysis of texts related to education or arising in the educational process. The aforementioned texts include the corpus of educational and teaching aids, texts of individual academic subjects, disciplines, topics, essays, written works, final qualifying works of students, essays made by school students, etc.