Cognitive networks reconstruct mindsets about STEM subjects and educational contexts in almost 1000 high-schoolers, University students and LLM-based digital twins

2026-02-16

AI Summary

This study investigates the cognitive and affective ambivalence students experience toward STEM—particularly mathematics and statistics—and explores the representational mechanisms underlying educational anxiety. Leveraging cognitive network science, the authors construct a Behavioral-Faculty Mental Network (BFMN) by reconstructing the affective-semantic structures of STEM concepts through free association tasks among high school students, undergraduates, and STEM professionals. For the first time, these human-derived networks are compared with digital twins generated by large language models (LLMs). Integrating affective annotation, Jaccard similarity, semantic frame extraction, and prompt engineering, the analysis reveals that mathematics and statistics are strongly associated with negative emotions and high abstraction. Notably, the “math–anxiety” link is significantly stronger in human networks than in LLMs, indicating that educational anxiety is experience-dependent and not readily replicable by current LLMs. This work pioneers a BFMN–LLM digital twin integration framework, quantifying affective halos, semantic overlap, and conceptual concreteness, thereby underscoring the irreproducibility of uniquely human educational anxiety in artificial systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Analogy
• Application Domains: Humanities & Computational Social Science
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Computational social science
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Attitudes toward STEM develop from the interaction of conceptual knowledge, educational experiences, and affect. Here we use cognitive network science to reconstruct group mindsets as behavioural forma mentis networks (BFMNs). In this case, nodes are cue words and free associations, edges are empirical associative links, and each concept is annotated with perceived valence. We analyse BFMNs from N = 994 observations spanning high school students, university students, and early-career STEM experts, alongside LLM (GPT-oss)"digital twins"prompted to emulate comparable profiles. Focusing also on semantic neighbourhoods ("frames") around key target concepts (e.g., STEM subjects or educational actors/places), we quantify frames in terms of valence auras, emotional profiles, network overlap (Jaccard similarity), and concreteness relative to null baselines. Across student groups, science and research are consistently framed positively, while their core quantitative subjects (mathematics and statistics) exhibit more negative and anxiety related auras, amplified in higher math-anxiety subgroups, evidencing a STEM-science cognitive and emotional dissonance. High-anxiety frames are also less concrete than chance, suggesting more abstract and decontextualised representations of threatening quantitative domains. Human networks show greater overlapping between mathematics and anxiety than GPT-oss. The results highlight how BFMNs capture cognitive-affective signatures of mindsets towards the target domains and indicate that LLM-based digital twins approximate cultural attitudes but miss key context-sensitive, experience-based components relevant to replicate human educational anxiety.

Problem

• STEM attitudes
• cognitive-affective dissonance
• math anxiety
• digital twins
• mindset representation

Innovation

• cognitive network science
• behavioural forma mentis networks
• STEM attitudes
• LLM digital twins
• semantic frames