Trait-Driven Neuroadaptive Interfaces in Smart Hospitality: A DEMATEL-Guided Agent-Based Simulation Approach

Heidari, Majid · 2025 · Crossref

DOI: 10.21203/rs.3.rs-8050980/v1

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the limitation of current smart hospitality systems, which prioritize behavioral prediction over psychological understanding, often neglecting how user traits influence interface perception. The research proposes a trait-driven neuroadaptive interface model that aligns system personalization with users' neuro-cognitive profiles—specifically emotional reactivity, cognitive load tolerance, and fairness sensitivity. Motivated by the gap between technical adaptability and user-centered fairness, the paper aims to demonstrate that personalization should be a dynamic response to internal user states rather than a static output based on inferred preferences. The methodology integrates the Decision-Making Trial and Evaluation Laboratory (DEMATEL) causal mapping with an agent-based simulation. First, seven experts provided pairwise ratings to establish a causal structure among three user traits and three interface demands (simplicity, ethical alignment, and information control). DEMATEL analysis identified "Emotional Reactivity" and "Ethical Alignment" as primary causal drivers, while "Cognitive Load Tolerance" and "Information Control" were identified as reactive receivers. These causal relationships informed the logic of an agent-based simulation involving 500 cognitively differentiated agents. Each agent, characterized by randomized trait values, interacted with one of three interface types: static, personalized, or fairness-aware. The simulation measured behavioral outcomes including trust, satisfaction, and cognitive load (via decision latency and reversals) to evaluate the impact of trait–interface congruence. The findings reveal that alignment between user traits and interface logic significantly enhances user experience. Fairness-aware interfaces, which embed ethical transparency and procedural justice, generated higher trust and satisfaction compared to static or purely personalized systems, particularly for agents with high fairness sensitivity. Emotional reactivity emerged as the most prominent driver in the system; agents with high emotional reactivity reported greater satisfaction when interfaces adapted their tone and complexity to match their affective state. Conversely, misalignment between interface logic and user traits—such as high cognitive load without corresponding simplification—led to increased cognitive overload, confusion, and disengagement. The results confirm that traits identified as dominant causal drivers in the DEMATEL model exert a stronger influence on trust and decision efficiency when integrated into adaptive rules. The study concludes that effective personalization requires a shift from preference matching to ethically responsive, psychologically aligned design. By embedding trait causality into system logic, developers can create interfaces that adapt to neuro-cognitive variability, thereby improving trust and reducing cognitive friction. The proposed framework offers a replicable process for trait-based adaptation, with implications for AI developers and tourism interface designers. Furthermore, the model’s integration of dual-process theory and affective computing suggests broader applicability to other adaptive systems in healthcare, education, and finance, where algorithmic decision aids must account for diverse human judgment and ethical expectations.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• automation