Decision Tree Algorithm for Visual Art Design in a Psychotherapy System for College Students.

Area of Science:

• Psychology
• Data Science
• Educational Psychology

Background:

• College student mental health is crucial for personal development.
• Identifying psychological problem precursors is essential for effective intervention.
• Data mining offers novel approaches to understanding complex psychological patterns.

Purpose of the Study:

• To uncover factors linked to psychological issues in college students using data mining.
• To develop art-based interventions for enhancing student mental well-being.
• To establish a comprehensive system for college student psychological treatment and support.

Main Methods:

• Data mining principles and algorithms (Apriori, ID3) were applied.
• Data preprocessing techniques were elaborated for psychological symptom data.
• Association rule mining and decision tree construction were utilized to analyze relationships among psychological dimensions.

Main Results:

• Strong association rules were extracted from data on obsessive-compulsive and interpersonal sensitivity symptoms.
• Potential relationships among nine psychological dimensions were identified.
• Classification rules for student psychological problems were discovered using a decision tree.

Conclusions:

• Data mining provides valuable insights into college student psychological health.
• Art design interventions can be effectively integrated into mental health treatment.
• The study offers a practical framework for school counseling and mental health education.