Hierarchical Latent Space Item Response Model for Analyzing Mental Health Vulnerability of Elementary School Students in South Korea

2026-03-13

AI Summary

Existing tools struggle to identify school-level patterns of psychological vulnerability among Korean elementary students from item response data. To address this gap, this study proposes the Hierarchical Latent Space Item Response Model (HLSIRM), which introduces— for the first time—a signed subject–item inner product interaction mechanism within a hierarchical framework to jointly model and visualize main effects at both school and individual levels, as well as their interactions with assessment items. Applied to data from 2,210 students across 35 elementary schools in Incheon, the model uncovers four distinct vulnerability dimensions, revealing that lack of prior counseling is a widespread risk factor, whereas stress, depression, and smartphone dependency are concentrated in specific schools. These findings provide empirical support for targeted, school-based mental health interventions.

Technology Category

• Machine Learning: Representation Learning
• Application Domains: Humanities & Computational Social Science
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Security and Privacy: Large-scale security measurements

Abstract

Mental health difficulties among elementary school students represent a growing public health concern in South Korea, yet analytical tools for identifying school-specific vulnerability patterns from item response data remain limited. We propose the hierarchical latent space item response model (HLSIRM), which adds hierarchical respondent effects and an inner-product latent interaction for signed respondent-item associations, yielding a unified interaction map that separates school, individual main effects from school/individual-item interactions. We apply HLSIRM to mental health vulnerability data from 2,210 elementary school students across 35 schools in Incheon, South Korea. Clustering item vectors by directional similarity identifies four empirically derived vulnerability domains. School-level analysis reveals that the absence of counseling experience is the primary vulnerability domain aligned with most school vectors, while stress, depression, and smartphone dependency concentrate in specific schools. Within-school analysis demonstrates how individual student positions in the interaction map translate into targeted intervention strategies that address school-specific needs.

Problem

• mental health vulnerability
• item response data
• school-specific patterns
• elementary school students
• hierarchical analysis

Innovation

• hierarchical latent space
• item response model
• signed respondent-item interaction
• directional similarity clustering
• mental health vulnerability