A method and system for generating a combination of psychological testing scales

Area of Science:

• Psychological assessment
• Psychometrics
• Computational psychology

Background:

• Traditional psychological testing scales have limitations in breadth and specificity.
• Comprehensive and individual assessment scales offer advantages but have complementary deficiencies.
• Current practical applications face challenges in optimizing scale selection.

Purpose of the Study:

• To propose a novel approach for optimizing psychological testing scales.
• To conceptualize scale and item selection as a multi-label classification problem.
• To develop an algorithm for generating optimized combinations of psychological scales.

Main Methods:

• Developed a hierarchical framework for psychological scale optimization.
• Introduced an algorithm for generating scale combinations.
• Utilized historical data analysis, item probability indices, dynamic content adaptation, item sequencing, and hierarchical system construction.

Main Results:

• Simulation experiments demonstrated enhanced efficiency and accuracy in psychological testing.
• The algorithm showed particular effectiveness in diagnosing moderate to severe symptoms.
• Lower accuracy was observed for mild symptoms due to their lower positive rate.

Conclusions:

• The proposed algorithm significantly improves the optimization of psychological testing scales.
• The approach excels in the assessment of moderate psychological symptoms.
• Further refinement may be needed for optimal performance with mild symptom assessment.