MATHEMATICAL MODELING AND STATISTICAL ANALYSIS METHODS FOR EVALUATING CHATBOT EFFECTIVENESS

Основное содержимое статьи

Asila Yusupova

Аннотация

This article examines, through a comprehensive approach, the use of mathematical methods to evaluate the technical and practical effectiveness of interactive chatbots employed in online education platforms. The main objective of the study is to quantitatively assess chatbot effectiveness and identify the most influential factors by applying statistical indicators, correlation and regression analysis, optimization, and mathematical model methods based on real data.


For this purpose, data collected from 24 chatbot sessions were analyzed using descriptive statistics, the Pearson correlation coefficient, a multiple regression model, forecasting techniques, and linear optimization methods, implemented step by step.


The results show that the variables X1 (Accuracy), X2 (Response Time), X3 (Completion Rate), and X4 (User Satisfaction) are the strongest determinants of chatbot effectiveness, while the remaining indicators play a supplementary diagnostic role. The reliability of the results was evaluated using the coefficient of variation, t-test, coefficient of determination (R²), MAPE, and RMSE criteria.


The obtained conclusions contribute to improving the technical and pedagogical effectiveness of interactive chatbots, identifying directions for their enhancement, and developing a methodology for conducting research based on mathematical methods for master’s students.

Информация о статье

Как цитировать
Yusupova , A. (2026). MATHEMATICAL MODELING AND STATISTICAL ANALYSIS METHODS FOR EVALUATING CHATBOT EFFECTIVENESS. Interpretation and Researches. извлечено от https://interpretationandresearches.uz/index.php/iar/article/view/3744
Раздел
Статьи
Биография автора

Asila Yusupova , Termez State University

Master’s student, 1st year Specialty: Computer Systems and Their Software

Библиографические ссылки

Zaripova M., Yusupova A. (2025). Onlayn ta’lim platformalari interaktiv chatbotlari samaradorligini kompleks baholash. «Yashil Iqtisodiyot Va Taraqqiyot» Jurnali, 3(11), 18–24. https://doi.org/10.5281/zenodo.17725285

Montgomery, D. C., & Runger, G. C. (2018). Applied statistics and probability for engineers (7th ed.). Wiley.

Triola, M. F. (2019). Elementary statistics (13th ed.). Pearson.

Devore, J. L. (2016). Probability and statistics for engineering and the sciences (9th ed.). Cengage Learning.

Gujarati, D. N., & Porter, D. C. (2009). Basic econometrics (5th ed.). McGraw-Hill/Irwin.

Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). Wiley.

Mustafakulov, S. (2017). Investment attractiveness of regions: Methodic aspects of the definition and classification of impacting factors. European Scientific Journal, 13(10), 433–449

Zaripova, M. D. (2019). Assessment of the quality of education in the higher education system. ISJ Theoretical & Applied Science, 11(79), 390–392. https://doi.org/10.15863/TAS.2019.11.79.63 (agar DOI mavjud bo‘lmasa, havola olib tashlanadi)

OpenAI. (2024). GPT-based Learning Applications: An Overview. OpenAI Technical Report, (TR-24-01).

Pavlik, M., Johnson, T., & Lee, A. (2023). User perception bias in human–AI interaction studies. In Proceedings of the ACM CHI Conference on Human Factors in Computing Systems (pp. 1–12). ACM Press. https://doi.org/10.1145/3544548.3580709