Educational analytics and adaptive training using student model in the intellectual learning systems

Main Article Content

Михаил Владиславович Каяшев
Денис Юрьевич Макаров
Антон Александрович Марченко

Abstract

For support of adaptive training and educational analytics in the intellectual learning systems, it is necessary to collect, process data on progress of the student and his various individual characteristics. It can be realized by means of the student model. The analysis of approaches to modeling of the student has shown that application of several types of models is an optimal solution, considering requirements to the learning system. Three approaches were chosen and united into one model: overlay, Bayesian network, error model. Use of overlay model allows to build individual trajectories of student training. Bayesian networks realize competence-based approach in training. The model of mistakes keeps track of wrong knowledge of the student and helps the student to correct them at early stages. The student model uniting in itself these approaches is more suitable for realization of the personalized training, allows to keep track of progress of the student according to various characteristics and also gives the chance to easily submit the card of subjects, knowledge, competence of the student of various areas in the form of the count that is quite convenient and clear representation.

Article Details

Author Biographies

Михаил Владиславович Каяшев

Master of the Higher School of Information Technologies and Intelligent Systems at Kazan (Volga region) Federal University.

Денис Юрьевич Макаров

Bachelor of the Higher School of Information Technologies and Intelligent Systems at Kazan (Volga region) Federal University.

Антон Александрович Марченко

Lecturer of the Higher School of Information Technologies and Intelligent Systems at Kazan (Volga region) Federal University, department assistant of software engineering.

References

1. Konstantina Chrysafiadi, Maria Virvou. Student modeling approaches: A literature review for the last decade // Expert Systems with Applications. 2013. No 40. P. 4715–4729.

2. Буль Е.Е. Обзор моделей студента для компьютерных систем обучения // Educational Technology & Society. 2003. № 6 (4). С. 245–250.

3. Атанов Г.А., Пустынникова И.Н. Обучение и искусственный интеллект, или основы современной дидактики высшей школы. Донецк: Изд-во ДОУ, 2002. 504 с.

4. Клюкин В.Э. Web-ориентированные интеллектуальные обучающие системы на основе нечеткого деятельностного подхода в обучении // Наука и образование. 2012. № 11. С. 450–461.

5. Cristina Conati. Bayesian Student Modeling // Advances in Intelligent Tutoring Systems. 2010. No 308. P. 281–289.

6. Хлопотов М.В. Применение байесовской сети при построении моделей для оценки уровня сформированности компетенций // Интернет-журнал «НАУКОВЕДЕНИЕ». 2014. № 5 (24). С. 1–28.

7. Дзюбан Ю., Болдак Л. Анализ алгоритмов вывода в Байесовских сетях доверия. В кн.: Високопродуктивні обчислення. Междунар. конф., Киев, 8–10 октября 2012. С. 167–169.

8. The Neo4j Graph Platform. https://neo4j.com/product/

9. Cypher. URL: http://neo4j.com/docs/developer-manual/current/cypher/

10. Sigma.js. URL: http://sigmajs.org

11. Chart.js. URL: https://www.chartjs.org

12. D3.js - Data-Driven Documents. URL: https://d3js.org


Most read articles by the same author(s)