CLASSIFICATION OF THE EDUCATIONAL TEXTS STYLES WITH THE METHODS OF ARTIFICIAL INTELLIGENCE

Journal Title: Journal of Baltic Science Education - Year 2017, Vol 16, Issue 3

Abstract

Modern educational methods emphasize the necessity to transfer knowledge instead of data or information within the educational process. Thus it is important to the educational texts supporting the educational process contain knowledge in a particular textual representation. But it is not trivial to decide whether the particular piece of text contain knowledge or not. The solution is to measure the similarity between the particular text structure and a typical structure of a knowledge-designed text. This research aims at analysing the classification ability of three commonly-used classification techniques: artificial neural networks (ANNs), classification and regression trees (CARTs) and decision trees (bigMLs) to separate texts or text fragments into two groups. The texts in the first group contain mainly data and information (common texts), the texts in the other group contain knowledge in one of the particular knowledge representations (knowledge texts). The sample of 120 text fragments was used for the analysis. The results show that the ANN techniques are significantly more able to make the right classification of the text than the CART or bigML ones, and evidence good classification abilities. Thus the ANN approach could broaden the set of methods used for evaluation of difficulty of educational texts or textbooks.

Authors and Affiliations

Tereza Horáková, Milan Houška, Ludmila Dömeová

Keywords

Related Articles

EFFECTIVENESS OF POLYA PROBLEM-SOLVING AND TARGET-TASK COLLABORATIVE LEARNING APPROACHES IN ELECTRICITY AMONGST HIGH SCHOOL PHYSICS STUDENTS

This research reports on the effectiveness of Polya Problem-Solving and Target-Task collaborative learning approaches in electricity amongst high school physics students. It also includes a gender focus. It was an experi...

GRADE 12 STUDENTS’ PERCEIVED SELF-EFFICACY TOWARDS WORKING LIFE SKILLS AND CURRICULUM CONTENT PROMOTED THROUGH SCIENCE EDUCATION

This research was based on the concern that students didn’t see the need for the acquisition of science skills and knowledge perceived as important in relation to different society issues and the world of work. The aim w...

ADOPTING IDEAS FROM CURRENT NORDIC TEACHER EDUCATION STRATEGIES TO INITIAL SCIENCE TEACHER EDUCATION

A key goal of initial teacher education in all countries is to educate quality teachers through a quality post-secondary programme and then support them in their careers through professional learning. However, there are...

EDUCATIONAL SHORT VIDEOS TO UTILIZE IN THE BIOCHEMISTRY LABORATORY: OPINIONS OF UNIVERSITY STUDENTS

This research aimed to reveal the opinions of the university students who conducted original educational videos context for the experiments in the Biochemistry laboratory course. Participants were fourth year students (N...

EXAMINING CHEMISTRY TEACHERS’ PERCEPTIONS OF THEIR INTERACTION WITH CURRICULUM MATERIALS: A QUANTITATIVE APPROACH

On the basis of the model of the interactive relationship between teachers and curriculum materials, this research proposed the four dimensions of the interaction of chemistry teachers with curriculum materials: ‘routine...

Download PDF file
  • EP ID EP437264
  • DOI -
  • Views 119
  • Downloads 0

How To Cite

Tereza Horáková, Milan Houška, Ludmila Dömeová (2017). CLASSIFICATION OF THE EDUCATIONAL TEXTS STYLES WITH THE METHODS OF ARTIFICIAL INTELLIGENCE. Journal of Baltic Science Education, 16(3), 324-336. https://www.europub.co.uk/articles/-A-437264