A Forced-Choice Neural Cognitive Diagnostic Model of Personality Testing

2025-07-20

AI Summary

Forced-choice (FC) personality assessments suffer from severe response biases, and conventional item response theory (IRT) and cognitive diagnosis models (CDMs) struggle to simultaneously satisfy item unidimensionality, accommodate multi-item blocks, and ensure parameter interpretability. Method: We propose the Forced-Choice Neural Cognitive Diagnosis Model (FC-NCDM), a deep learning framework that employs multilayer neural networks to model nonlinear interactions between latent traits and item features, uniformly handles three common FC block types, enforces monotonicity constraints for parameter interpretability, and explicitly incorporates the unidimensionality assumption per item. Contribution/Results: Extensive simulations and real-data experiments demonstrate that FC-NCDM substantially improves measurement accuracy and robustness against response biases. It yields interpretable individual trait profiles and diagnostic item parameters—overcoming fundamental limitations of traditional IRT and CDM approaches in FC settings.

Technology Category

• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In the smart era, psychometric tests are becoming increasingly important for personnel selection, career development, and mental health assessment. Forced-choice tests are common in personality assessments because they require participants to select from closely related options, lowering the risk of response distortion. This study presents a deep learning-based Forced-Choice Neural Cognitive Diagnostic Model (FCNCD) that overcomes the limitations of traditional models and is applicable to the three most common item block types found in forced-choice tests. To account for the unidimensionality of items in forced-choice tests, we create interpretable participant and item parameters. We model the interactions between participant and item features using multilayer neural networks after mining them using nonlinear mapping. In addition, we use the monotonicity assumption to improve the interpretability of the diagnostic results. The FCNCD's effectiveness is validated by experiments on real-world and simulated datasets that show its accuracy, interpretability, and robustness.

Problem

• Develops a neural model for forced-choice personality tests
• Improves interpretability of test results using neural networks
• Validates model accuracy on real and simulated datasets

Innovation

• Deep learning-based Forced-Choice Neural Cognitive Diagnostic Model
• Interpretable participant and item parameters
• Monotonicity assumption enhances interpretability