<![CDATA[The increasing use of Artificial Intelligence (AI) in education has influenced various learning activities. However, excessive AI usage has the potential to create dependency patterns that may affect students’ learning independence and critical thinking abilities. This study aims to analyze patterns of AI usage dependency in learning activities using a machine learning approach and to interpret the factors influencing such dependency. The analysis was conducted using a publicly available dataset representing usage intensity, session duration, AI assistance level, repeated usage behavior, and students’ academic characteristics. The research stages consisted of data preprocessing, categorical variable encoding, feature engineering, the construction of the Knowledge Dependency Level variable, class imbalance handling using SMOTE, and model evaluation using Stratified 5-Fold Cross Validation. The dataset was divided into 80% training data and 20% testing data, then modeled using Logistic Regression, Random Forest, and XGBoost. The results showed that XGBoost achieved the best performance with an accuracy of 0.6845, precision of 0.7288, recall of 0.6845, F1-score of 0.7028, and an AUC value of 0.860, indicating better discrimination capability compared to Random Forest and Logistic Regression. To support the knowledge discovery process, an interpretative analysis using SHAP was conducted to identify the contribution of each feature to the classification results. The interpretation revealed that SatisfactionRating was the most dominant feature influencing the prediction of AI usage dependency levels, followed by FinalOutcome, while academic factors such as StudentLevel and Discipline contributed relatively less. These findings transform previously implicit AI usage behavior patterns into explicit knowledge.]]>
