CC BY
9Impact Factor: SJIF 2021 - 5.81 2022 - 5.94
ПЕДАГОГИЧЕСКИЕ НАУКИ PEDAGOGICAL SCIENCES
UDC 004.855
E-TEXTBOOK WITH INTELLIGENT LEARNING SYSTEMS BASED ON NEURAL
NETWORK TECHNOLOGIES
BALGOZHINA GULMIRA BEKETOVNA
Lead Expert in the Research and Textbook Programs Department RSE on REM "Republic Scientific and Practical Center for Expertise of the Content of Education",
Astana, Kazakhstan
Annotation. The relevance of developing an e-textbook with intelligent learning systems is driven by current trends in digitalization of education and the integration of innovative technologies into the learning process. In the context of rapidly increasing information volumes and evolving professional qualifications requirements, traditional teaching methods often fail to provide adequate personalization and interactivity. Intelligent systems integrated into educational resources can tailor the learning material to each learner's individual needs, thereby enhancing the effectiveness of knowledge acquisition and facilitating the learning process.
Moreover, the use of such systems promotes the development of self-learning skills, critical thinking, and problem-solving abilities, which are essential competencies for successful professional activity in a digital economy. Therefore, the creation of e-textbooks with intelligent learning systems addresses the challenges of modern education and contributes to its further modernization and improvement in the quality of specialist training.
Keywords: e-textbook, neural network technologies, intelligent learning systems, personalized learning, adaptive educational resources, digital education, automated knowledge assessment, artificial intelligence in education.
Modern educational technologies are evolving rapidly, with one of the key directions being the integration of intelligent systems into the learning process. Neural network technologies, widely used in various fields, are increasingly being applied in education. E-textbooks with built-in intelligent systems enable the personalization of the learning process by adapting materials to the knowledge level and individual characteristics of each learner. This article discusses the development of an e-textbook using neural network technologies and presents a small experiment demonstrating the effectiveness of this approach.
Neural networks, the foundation of modern artificial intelligence systems, are applied in various domains due to their ability to learn and adapt. In education, they can be used to analyze learner's knowledge levels, predict learning success, and develop adaptive learning programs [1]. E-textbooks equipped with neural network modules can dynamically modify content and difficulty levels depending on the learner's progress.
The use of such technologies in education offers several advantages:
1. Personalized Learning - Systems can tailor individual tasks and materials based on a learner's previous responses.
2. Adaptivity - The textbook can change content in real-time and provide recommendations for deeper knowledge acquisition.
3. Automated Knowledge Assessment - The system can automatically assess progress, identify weak areas, and offer improvement suggestions [2].
An experiment was conducted at an educational institution in Kazakhstan.
Objective of the experiment: To explore the impact of using an e-textbook with a neural network-based adaptive system on the effectiveness of knowledge acquisition.
Methodology:
1. Participants: 20 learners were selected for the experiment and divided into 2 groups of 10: ✓ Control group: used a standard e-textbook without intelligent systems.
Impact Factor: SJIF 2021 - 5.81 2022 - 5.94
ПЕДАГОГИЧЕСКИЕ НАУКИ PEDAGOGICAL SCIENCES
✓ Experimental group: used an e-textbook with a neural network system that adapted content based on the learner's level [2].
2. Learning material: both groups studied the same topic (e.g., the basics of Python programming), using e-textbooks with identical initial content. However, the experimental group's textbook included a neural network system that adjusted the exercises and theoretical materials.
3. Process: The study lasted one week. At the end of the period, both groups completed a knowledge assessment test.
4. Evaluation of results: The test results were analyzed to assess the difference in material retention between the control and experimental groups.
Results:
Learners who used the e-textbook with the neural network system scored, on average, 15% higher than those in the control group.
The experimental group noted that the textbook provided additional materials and exercises that helped them better understand complex topics.
The control group often encountered uniform tasks that did not match their skill levels, which reduced their motivation to continue learning.
The results demonstrate that e-textbooks with integrated neural network systems contribute to more effective knowledge acquisition. Adapting learning materials to the learner's level helps avoid overload and increases interest in learning. Moreover, real-time automatic feedback allows learners to identify knowledge gaps and immediately address them.
Neural network technologies have the potential to become a key element in the future of education, not only improving the material retention process but also optimizing the interaction between teacher and learner.
E-textbooks with intelligent systems based on neural network technologies hold significant potential for improving the educational process. The experiment confirmed that the use of such textbooks enhances learning efficiency by tailoring materials to individual learner needs. Further research is planned to expand the experiment with a larger number of participants and across different educational disciplines to examine the broader impact of neural network technologies on various aspects of the learning process.
REFERENCES
1. Serik, M., Nurgalyeva, S., Balgozhina, G. Introducing robotics with computer neural network technologies to increase the interest and inventiveness of students. World Transactions on Engineering and Technology Education,-2022. V. 20 (1), pp. 33-38. ISSN:1446-2257 http://www.wiete.com.au/journals/WTE&TE/Pages/TOC V20N1.html
2. Shamsutdinova T.M. Problems and Prospects for the Application of Neural Networks for the Sphere of Education. Open Education. 2022;26(6):4-10. (In Russ.) https://doi.org/10.21686/1818-4243-2022-6-4-10
