Cognitive Linguistic Identity Fusion Score (CLIFS): A Scalable Cognition-Informed Approach to Quantifying Identity Fusion from Text

2025-09-20

AI Summary

This study addresses the challenge of automating and scaling the quantification of identity fusion—the psychological linkage between individuals and collective/abstract goals. To this end, we propose CLIFS (Cognitive Linguistics-Informed Fusion Scoring), an end-to-end text analysis method integrating cognitive linguistics principles with large language models (LLMs). CLIFS is the first approach to jointly leverage metaphor identification—as a cognitive proxy for identity fusion—with LLM-based semantic understanding to enable fully automated, annotation-free scoring of fusion intensity. In benchmark evaluations, CLIFS significantly outperforms conventional psychometric scales and existing NLP methods in accuracy. When applied to violent risk assessment, it achieves over a 240% improvement in performance relative to the best prior baseline. This work establishes a novel NLP task—computational social cognition modeling—and advances methodological rigor at the intersection of computational linguistics and social psychology. The model and code are publicly released.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Natural Language Processing: Safety and Robustness
• Computer Vision: Language and Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Quantifying identity fusion -- the psychological merging of self with another entity or abstract target (e.g., a religious group, political party, ideology, value, brand, belief, etc.) -- is vital for understanding a wide range of group-based human behaviors. We introduce the Cognitive Linguistic Identity Fusion Score (CLIFS), a novel metric that integrates cognitive linguistics with large language models (LLMs), which builds on implicit metaphor detection. Unlike traditional pictorial and verbal scales, which require controlled surveys or direct field contact, CLIFS delivers fully automated, scalable assessments while maintaining strong alignment with the established verbal measure. In benchmarks, CLIFS outperforms both existing automated approaches and human annotation. As a proof of concept, we apply CLIFS to violence risk assessment to demonstrate that it can improve violence risk assessment by more than 240%. Building on our identification of a new NLP task and early success, we underscore the need to develop larger, more diverse datasets that encompass additional fusion-target domains and cultural backgrounds to enhance generalizability and further advance this emerging area. CLIFS models and code are public at https://github.com/DevinW-sudo/CLIFS.

Problem

• Quantifying identity fusion from text automatically and scalably
• Improving violence risk assessment through cognitive-linguistic analysis
• Developing cognition-informed metrics for group behavior understanding

Innovation

• Integrates cognitive linguistics with large language models
• Uses implicit metaphor detection for automated assessment
• Outperforms existing automated approaches and human annotation