Knowledge Resource
Research Summary: Value Faces: Surfacing How Self-Presentation Shifts Across Relationships
- Original authors
- Attribution requires verification
- Original source
- arXiv — Computers and Society
- Summary & Analysis prepared by
- Aziz Shuaib Ausi
- Resource type
- Research Summary / Knowledge Resource
- Resource published on AZIZ OS
- 18 September 2026
- Reading time
- 1 min
- Publication type
- Knowledge Resource
- Availability
- Open access
About this Summary & Analysis
AZIZ OS provides independently prepared summaries and analytical interpretations of externally published research and knowledge sources. The underlying works remain attributable to their original authors and rights holders. This resource is intended to improve accessibility and understanding and does not replace the original publication.
A novel system called 'Value Faces' has been developed to analyze how individuals' self-presentation shifts across different relationships, specifically in terms of the values they express. This computational approach, based on Schwartz's ten basic human values, processes chat histories to generate distinct value profiles for various relationships. Initial mixed-methods research suggests that individuals' demonstrated values vary significantly depending on the relationship context.
Why it matters
Understanding how individuals express different values in various relationship contexts can significantly inform strategies related to internal communications, team dynamics, and external engagement. This insight allows for more tailored and effective interactions, as it highlights the nuanced nature of human value expression in diverse professional and personal settings.
Key insights
- Individuals present different aspects of themselves across relationships, extending to the values they foreground or background.
- Computational work can capture variation in communication style and expressed values.
- 'Demonstrated values' are defined as relationship-specific expressions of principles and their balance.
- Value Faces is a system that analyzes chat histories using Schwartz's ten basic human values to produce distinct value profiles for different relationships.
- Early research (N=18) indicates that value profiles indeed shift across relationships.
Source
arXiv — Computers and Society — https://arxiv.org/abs/2609.19581
Related intelligence and resources
Previous
ResumeShield: Channel Separation and an Open Benchmark for Indirect Prompt Injection in AI Resume Screening
Next
Locating Translation as a Craft in the Age of AI
AI Should Facilitate Democratic Deliberation at Scale
Knowledge Resource
''Bless his heart... he thought all we did was push a button": Understanding Worker Challenges with U.S. Election Technology
Knowledge Resource
Geopolitical Divisions Across Languages in Large Language Models
Knowledge Resource
Utilizing AI-Driven Project Management Tools for Optimized Talent Management in HRM: A Framework for Enhanced Resource Allocation and Performance Prediction
Knowledge Resource
Funding the runners-up beats a golden ticket
Knowledge Resource
Language-model groups overstate consensus when replaying human deliberation on a reasoning task
Knowledge Resource
Citation
Cite the original work (APA 7)
The original source is authoritative for this citation. Cite the source publication directly — this attribution is pending verification. Open the original source.
Verification
This is an authenticated AZIZ OS resource record.
- Verification ID
- ASA-EXE-2026-00719
- Version
- v1.0 · r0
- Issued
- 18 September 2026
- Resource prepared by
- Aziz Shuaib Ausi
- Resource status
- Research Summary / Knowledge Resource
- Underlying work
- Value Faces: Surfacing How Self-Presentation Shifts Across Relationships
- Original authors
- Attribution requires verification
- Original source
- arXiv — Computers and Society
- Provenance status
- Attribution requires verification
- Rights
- Underlying publication rights remain with the respective copyright holder(s). Refer to the original source for authoritative publication and licensing information.
This verification confirms the AZIZ OS resource record and its documented provenance. It does not establish authorship of the underlying external work.