Evaluation of attitudes of university students towards artificial intelligence using data mining methods

Area of Science:

• Educational Technology
• Artificial Intelligence
• Data Mining

Background:

• Understanding university students' attitudes towards artificial intelligence (AI) is crucial for developing effective AI literacy programs.
• Previous research has explored AI perceptions, but few studies employ advanced data mining techniques for detailed classification.

Purpose of the Study:

• To analyze and classify university students' attitudes towards artificial intelligence using various data mining algorithms.
• To compare the performance of different machine learning models in categorizing AI attitudes.

Main Methods:

• Collected data from 1379 university students using a scale to assess attitudes towards AI.
• Employed data mining techniques, including MLP, Decision Tree, KNN, XGBoost, Random Forest, CatBoost, and SVM.
• Utilized 5-fold cross-validation and calculated accuracy, precision, recall, and F1 score for model evaluation.

Main Results:

• The Support Vector Machine (SVM) algorithm achieved the highest F1-score accuracy at 95.52%.
• CatBoost (93.66%), Random Forest (92.56%), and XGBoost (92.36%) also demonstrated high performance.
• MLP (81.87%) and Decision Tree (82.72%) models showed lower classification success rates.

Conclusions:

• Advanced classification algorithms, particularly SVM, are effective tools for analyzing student attitudes toward AI.
• Findings can inform educational policies and strategies to enhance AI literacy among university students.