TR-VABML: Enhancing Turkish vocabulary acquisition through adaptive machine learning classification

Conventional vocabulary assessments emphasize precision rather than hesitation and rapidity. A machine learning system was developed utilizing behavioral analysis and linguistic insights to identify vocabulary gaps in Turkish language learners. This system integrates hesitation counts, reaction times, and answer attempts with word difficulty and thematic elements. Vocabulary strength was computed using a rule-based equation derived from behavioral indications. With 89% accuracy, 86% precision, 91% recall, and an 88% F1 score, the model showed better performance than the linear and Poisson kernel alternatives. By effectively separating complex interactions, the RBF kernel minimizes unnecessary actions and ensures accurate identification of real shortages. • Innovative Machine Learning Application: Introduces a novel system for adaptive Turkish vocabulary acquisition using machine learning classification techniques. • Comprehensive Data Collection: Utilizes a diverse set of behavioral data (response time, hesitation, correctness, and word difficulty) from real users to enhance learning personalization. • Advanced Model Evaluation: Achieves an 89% accuracy, with high precision (86%), recall (91%), and F1-score (88%) in detecting vocabulary weaknesses, demonstrating robust performance. • Stratified 5-Fold Cross-Validation: Ensures unbiased training and testing, preserving class distribution for more reliable model generalization. • Integration with multiple technology: Features seamless integration with Unity-based applications, firebase and machine leaning for real-time vocabulary augmentation and user activity assessment. • Practical Educational Impact: The model’s performance suggests high potential for enhancing personalized vocabulary learning interventions in real-world settings.