Enterprise AI Research Analysis
Evaluation of attitudes of university students towards artificial intelligence using data mining methods
This study analyzes university students' attitudes towards artificial intelligence. Within the scope of the research, the data obtained from 1379 students through scale application were classified into three classes as "Insufficient”, “Sufficient” and “Strongly Sufficient” according to their attitudes towards artificial intelligence. The data was classified by data mining methods. For this purpose, MLP, Decision Tree, KNN, XGBoost, Random Forest, CatBoost and SVM algorithms were used. The performance of the model was evaluated with a 5-fold cross-validation method. For each algorithm, basic metrics such as accuracy, precision, recall and F1 score were calculated and the classification performance was compared. According to the results, the highest F1-Score accuracy rate was 95.52% for the SVM algorithm. This was followed by CatBoost (93.66%), Random Forest (92.56%) and XGBoost (92.36%). The lowest success rates were observed in MLP (81.87%) and Decision Tree (82.72%) models. Confusion matrices revealed a tendency for frequent confusion with other classes, especially in the Strongly Sufficient class. The study concluded that advanced classification algorithms provide powerful and reliable tools for analyzing students' attitudes towards artificial intelligence. These findings may contribute to the development of educational policies and strategies for AI literacy.
Quantifiable Impact & Key Findings
This research provides critical insights into student attitudes towards AI, leveraging advanced data mining to identify key patterns and inform educational strategies. Our analysis highlights:
0
Highest F1-Score (SVM)
0
Lowest F1-Score (MLP)
0
University Students Surveyed
0
Attitude Classes Identified
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
Robust Data Mining Approach
This study aimed to evaluate university students' attitudes towards artificial intelligence using data mining methods. The SATAI scale, developed by Suh and Ahn, was utilized for data collection. A total of 1379 university students from Turkey participated in an online survey conducted between April 14 and April 27, 2025. The dataset comprised 29 variables and students' attitudes were classified into three distinct categories: 'Insufficient' (210 students), 'Sufficient' (502 students), and 'Strongly Sufficient' (667 students). To achieve this classification, a suite of data mining algorithms was employed, including MLP, Decision Tree, KNN, XGBoost, Random Forest, CatBoost, and SVM. The performance of these models was rigorously assessed using a 5-fold cross-validation method, calculating key metrics such as accuracy, precision, recall, and F1-score.
Comparative Model Performance
The performance analysis revealed significant differences across the employed data mining algorithms. The SVM algorithm achieved the highest F1-score at 95.52%, demonstrating superior classification capability with an accuracy of 95.58%, precision of 95.86%, and recall of 95.58%. Closely following were CatBoost (93.66% F1-score), Random Forest (92.56% F1-score), and XGBoost (92.36% F1-score), all exhibiting high classification performance. In contrast, KNN achieved an F1-score of 88.71%, while Decision Tree (82.72% F1-score) and MLP (81.87% F1-score) showed the lowest success rates. The study emphasized the F1-score as a more reliable metric due to partial class imbalance in the dataset. Confusion matrices indicated a notable tendency for misclassification within the 'Strongly Sufficient' class, often confused with 'Sufficient' or 'Insufficient', highlighting the complexity of accurately distinguishing nuanced attitude levels. Pairwise Wilcoxon signed-rank tests confirmed statistically significant performance differences among most algorithm pairs, with XGBoost and Random Forest being an exception.
Influential Factors on AI Attitudes
Analysis of feature importance provided crucial insights into the factors most influencing university students' attitudes toward AI. Across multiple algorithms (Random Forest, Boosting models, and SVM), certain features consistently ranked highest. Specifically, statements like "I am interested in the development of AI", "I want to work in the field of AI", and "I like using objects related to AI" were identified as critically important determinants. These findings underscore that students' personal interest in AI, their career intentions related to AI, and their active engagement with AI-related tools are strong predictors of their overall attitudes. This consistency across diverse models reinforces the reliability of these insights. These insights are valuable for designing targeted educational interventions, such as fostering AI interest, providing AI-related career guidance, and enhancing hands-on experience with AI tools to improve AI literacy and positive attitudes among students.
Enterprise Process Flow
Data Obtaining
→
Target Group
→
Data Pre-Processing
→
Classes
→
Choosing ML Models
→
Performance Metrics & Evaluation
95.52%
Highest F1-Score Achieved with SVM Algorithm
| Method | F1-Score (%) | Accuracy (%) | Precision (%) | Recall (%) |
|---|---|---|---|---|
| MLP | 81.87 | 81.94 | 82.48 | 81.94 |
| Decision Tree | 82.72 | 82.74 | 82.72 | 82.74 |
| KNN | 88.71 | 88.76 | 88.91 | 88.76 |
| XGBoost | 92.36 | 92.39 | 92.43 | 92.39 |
| Random Forest | 92.56 | 92.60 | 92.78 | 92.60 |
| CatBoost | 93.66 | 93.69 | 93.79 | 93.69 |
| SVM | 95.52 | 95.58 | 95.86 | 95.58 |
Project Your AI Impact
Estimate the potential efficiency gains and cost savings for your organization by integrating AI-driven insights.
Projected Annual Savings
$0
Annual Hours Reclaimed
0
Your AI Implementation Roadmap
Leverage these insights to build a strategic plan for integrating AI into your educational or organizational framework, fostering AI literacy and positive attitudes.
Phase 1: Foundational Data Collection & Assessment
Conduct initial surveys and gather baseline data on student attitudes towards AI. Establish ethical guidelines and consent processes to ensure responsible data handling.
Phase 2: Advanced Model Development & Validation
Implement and fine-tune data mining algorithms to classify student attitudes. Validate model performance with cross-validation and confusion matrix analysis to ensure reliability and identify areas of nuance.
Phase 3: Strategic Policy Formulation
Translate analytical findings into actionable educational policies. Focus on integrating AI literacy and ethical considerations into university curricula, based on a holistic understanding of student perceptions.
Phase 4: Targeted Curriculum Integration & Support
Design and implement specific modules to foster AI interest, provide career guidance, and enhance hands-on experience with AI tools, based on identified key influencing factors such as personal interest and career intentions.
Phase 5: Continuous Monitoring & Adaptive Enhancement
Establish mechanisms for ongoing evaluation of policies and curricula. Regularly assess student attitudes and model performance, adapting strategies to evolving technological landscapes and student needs to ensure long-term effectiveness.
Ready to Transform Your Organization with AI?
Unlock the full potential of AI insights. Schedule a personalized consultation to discuss how our advanced analytical solutions can drive your strategic initiatives.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat