Leveraging Mental Models for Human-Centered Explanations: A Systematic Design Approach Illustrated by Explainable Fake Review Identification

Sidra Naveed; Md Shajalal; Gunnar Stevens; Alexander Boden

cs.HCOct 17, 2026

Leveraging Mental Models for Human-Centered Explanations: A Systematic Design Approach Illustrated by Explainable Fake Review Identification

Authors: Sidra Naveed, Md Shajalal, Gunnar Stevens, Alexander Boden

Organizations: University of Siegen, Germany · Hochschule Bonn-Rhein-Sieg

Abstract

Explainable AI (XAI) often prioritizes model fidelity over user intelligibility, yielding explanations that satisfy technical transparency yet fail to support human sense-making. We propose a human-centered approach, MIND-X (Mental-model INtegrated Design for eXplainability), which aligns explanations with users' mental models, commonsense concepts, and judgment heuristics. Using fake review detection as a case study, we contribute: (1) a qualitative study (n=10) that elicits how people assess review credibility and produces an actionable, design-guiding taxonomy of perceptual cues; (2) a set of design principles that link those cues to explanation strategies and prompt LLMs to generate adaptive, language-based explanations; and (3) a quantitative evaluation (n=166) showing that these explanations offer distinct advantages over token-level transparency methods widely used in explainable text classification in terms of understandability, satisfaction, perceived trust, persuasiveness, and decision-making support. Rather than claiming general superiority, our evaluation illustrates how grounding explanations in users' everyday reasoning practices can produce more intelligible and context-sensitive accounts. Our findings advance human-centered explanation design beyond a mere "gloss of transparency," demonstrating that a mental-model-aligned design process can improve intelligibility and support accountability across user-centered explanation tasks.

Figures & tables

Figure 1. Designing human-centered explanation following MIND-X: From domain models to tailored explanations.

Participant	Occupation	Field of Study	Frequency of Online Purchase	Frequency of Reading Online Reviews
P1	Doctoral Student	HCI	Monthly	Often for expensive items; Rarely for low-cost
P2	Trainee Engineer	Computer Science	Every 1–2 months	Always before purchase
P3	Master’s Student	HCI	As needed	Always before purchase
P4	Researcher	Global Politics	1–2/week	Always before purchase
P5	Master’s Student	Visual Computing	2–3/month	Often for all items
P6	Postdoc Researcher	Political Economy	1–2/month	Always before purchase

Table 1. Demographics of participants and their personal experiences with online shopping and reviews

Characteristic	$n$	%
Gender
Female	96	58
Male	70	42
Non-binary / Prefer not to disclose	0	0
Age
$M$ = 39.2, $SD$ = 12.7, Range = 20.0–75.0

Table 2. Demographic and review characteristics of the Prolific sample (

N=166

Construct	Items (comparative wording)	Reference
Understandability	• I found the explanation easier to understand. • The explanation was clearer and less ambiguous. • The explanation made the AI’s decision-making process more transparent.	( Hoffman et al., 2018 ; Naveed et al., 2024 )
Satisfaction	• I am more satisfied with the explanation. • The explanation met my expectations better.	( Hoffman et al., 2018 )
Trust	• The explanation increased my trust in the system’s decision. • The explanation made me believe the AI made the right decision.	( Amershi et al., 2019 )
Decision Support	• The explanation helped me make a better decision. • The explanation made me feel more confident in classifying the review.	( Naveed et al., 2024 ; Kulesza et al., 2015 )
Persuasiveness	• The explanation convinced me more that the review was (not) fake. • The explanation influenced my opinion about the review more.	( Kulesza et al., 2015 ; Amershi et al., 2019 )
Cognitive Load	• It was more mentally demanding to understand the explanation. • I had to put more effort into making sense of the explanation.	( Naveed et al., 2024 )

Table 3. Operationalization of explanation quality constructs through comparative questionnaire items.

Theme	Cue	Description
Simple Language and Conciseness	Plain, everyday words; short reviews	Signals authenticity; resembles ordinary consumer voice
Excessive Detail	Overly long or elaborate descriptions	Triggers suspicion; feels like product description
Balanced Pros and Cons	Mentions both strengths and weaknesses	Signals honesty and credibility
Emotional Authenticity and Redundancy	Genuine joy; repeated phrases; exaggerated positivity	Natural emotion increases authenticity; over-positivity raises doubt
Persuasive Intent	Repetitive recommendation; promotional tone	Feels promotional; undermines trust
Visual Presentation	Everyday, casual photos vs. polished, staged photos	Casual photos signal authenticity; staged images trigger suspicion

Table 4. Summary of cues participants used to evaluate reviews as fake

Panel of Figure 2 — Figure 2. Meta-prompt template designed to generate human-centered, domain-sensitive explanations.

Panel of Figure 3 — Figure 3. Meta-Prompt designed to generate context-specific explanations tailored to the intended target group.

Panel of Figure 4 — Figure 4. Two explanation types for fake review detection. Top: propositional, checklist-like rationales; Bottom: in-situ visual cues.

Issue	Language-based (top)	Word-highlighting (bottom)
Visual design
	• Checklist-like bullet points	• In-situ, token-level saliency overlay
	• Textual marking of key arguments	• Graphical highlighting of salient words
	• Green/red-coded classification (entire box)	• Green/red-coded classification (word-based)
Space design
	• Separate panel; detached from input	• Co-located with the source text

Table 5. Comparison structured by visual design, semantic–cognitive, and application levels.

Construct	AVE	Composite Reliability	Cronbach’s $\alpha$
Cognitive Load	.79	.88	.87
Satisfaction	.75	.86	.86
Decision Support	.74	.85	.85
Trust	.71	.83	.83
Understandability	.71	.88	.88
Persuasiveness	.59	.73	.71

Table 6. Convergent validity indices (sorted by AVE, then CR, then Cronbach’s

\alpha

	Cl	Sa	Ds	Tr	Un	Pe		Cl	Sa	Ds	Tr	Un	Pe
Cl	.89						Cl	–
Sa	.35	.87					Sa	.36	–
Ds	.32	.93	.86				Ds	.33	.92	–
Tr	.33	.95	.96	.84			Tr	.34	.95	.96	–
Un	.33	.99	.95	.97	.84		Un	.34	.99	.95	.97	–
Pe	.21	.88	.95	.88	.87	.76	Pe	.21	.89	.96	.89	.88	–

Table 7. Discriminant validity indices

Construct	$M$	$SD$	95% CI	$t(995)$	$p$	$p_{\text{bonf}}$	$p_{\text{FDR}}$	$d$
Satisfaction	$1.33$	$1.04$	[1.26, 1.39]	$40.23$	$<.001$	$<.001$	$<.001$	$1.27$
Understandability	$1.31$	$1.02$	[1.25, 1.38]	$40.76$	$<.001$	$<.001$	$<.001$	$1.29$
Trust	$1.22$	$1.03$	[1.16, 1.29]	$37.56$	$<.001$	$<.001$	$<.001$	$1.19$
Decision Support	$1.20$	$1.06$	[1.13, 1.26]	$35.70$	$<.001$	$<.001$	$<.001$	$1.13$
Persuasiveness	$1.04$	$1.01$	[0.98, 1.10]	$32.55$	$<.001$	$<.001$	$<.001$	$1.03$
Cognitive Load a	$0.83$	$1.25$	[0.75, 0.91]	$20.97$	$<.001$	$<.001$	$<.001$	$0.66$

Table 8. Descriptive statistics and one-sample

t

-tests for explanation quality constructs (

n_{p}=166

n_{r}=996

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 5 — Figure 5. Explanations generated by both systems for Review 1

Panel of Figure 6 — Figure 6. Explanations generated by both systems for Review 2

Panel of Figure 7 — Figure 7. Explanations generated by both systems for Review 3

Panel of Figure 8 — Figure 8. Explanations generated by both systems for Review 4

Panel of Figure 9 — Figure 9. Explanations generated by both systems for Review 5

Panel of Figure 10 — Figure 10. Explanations generated by both systems for Review 6

Explainable Artificial Intelligence

Explainable artificial intelligence develops ways to make AI decisions understandable, testable, and useful to people.

See all 324 papers

CoAX: Cognitive-Oriented Attribution eXplanation User Model of Human Understanding of AI Explanations
Apr 30, 2026Louth Bin Rawshan, Zhuoyu Wang, Brian Y. LimFeature Attribution Explainable Artificial Intelligence
National University of Singapore, Singapore
Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations
Oct 12, 2026Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan +2Explainable Artificial Intelligence Feature Selection
School of Computer Science and Information Technology, University College Cork, Ireland · Centre for Research Training in Artificial Intelligence, University College Cork, Ireland · Department of Methodology and Statistics, Tilburg University +1
XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?
Sep 8, 2026Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein +1Explainable Artificial Intelligence LLM-as-a-Judge
LMU Munich, Germany · Chair of Information Systems, School of Business and Economics, Humboldt-Universität zu Berlin, Germany · Scientific Computing Center, Karlsruhe Institute of Technology, Germany +1

Apr 30, 2026J/K move · Enter open · S save

CoAX: Cognitive-Oriented Attribution eXplanation User Model of Human Understanding of AI Explanations

Louth Bin Rawshan, Zhuoyu Wang, Brian Y. Lim

National University of Singapore, Singapore

Feature Attribution Explainable Artificial Intelligence Human-AI Decision Making Explainability Evaluation

Open paper AskPDF arXiv

Explainable AI (XAI) aims to improve user understanding and decisions when using AI models. However, despite innovations in XAI, recent user evaluations reveal that this goal remains elusive. Understanding human cognition can help explain why users struggle to effectively use AI explanations. Focusing on reasoning on structured (tabular) data, we examined various reasoning strategies for different XAI methods (none, feature importance, feature attribution) in the decision task of anticipating AI decisions (i.e., forward simulation). We i) elicited reasoning strategies from a formative user study, and ii) collected decisions from a summative user study. Using cognitive modeling, we implemented the processes underlying each reasoning strategy and evaluated their alignment with human decision-making. We found that our models better fit human decisions than baseline machine learning proxies, providing insights into which reasoning strategies are (in)effective. We then demonstrate how the fitted model can be used to form hypotheses and investigate research questions that are costly to study with real human participants. This work contributes to debugging human understanding of XAI, informing the future development of more usable and interpretable AI explanations.

	Cl	Sa	Ds	Tr	Un	Pe		Cl	Sa	Ds	Tr	Un	Pe
Cl	.89						Cl	–
Sa	.35	.87					Sa	.36	–
Ds	.32	.93	.86				Ds	.33	.92	–
Tr	.33	.95	.96	.84			Tr	.34	.95	.96	–
Un	.33	.99	.95	.97	.84		Un	.34	.99	.95	.97	–
Pe	.21	.88	.95	.88	.87	.76	Pe	.21	.89	.96	.89	.88	–

	Cl	Sa	Ds	Tr	Un	Pe		Cl	Sa	Ds	Tr	Un	Pe
Cl	.89						Cl	–
Sa	.35	.87					Sa	.36	–
Ds	.32	.93	.86				Ds	.33	.92	–
Tr	.33	.95	.96	.84			Tr	.34	.95	.96	–
Un	.33	.99	.95	.97	.84		Un	.34	.99	.95	.97	–
Pe	.21	.88	.95	.88	.87	.76	Pe	.21	.89	.96	.89	.88	–

Abstract

Explainable Artificial Intelligence

Explore similar work

CoAX: Cognitive-Oriented Attribution eXplanation User Model of Human Understanding of AI Explanations

Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations

XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?

	Cl	Sa	Ds	Tr	Un	Pe		Cl	Sa	Ds	Tr	Un	Pe
Cl	.89						Cl	–
Sa	.35	.87					Sa	.36	–
Ds	.32	.93	.86				Ds	.33	.92	–
Tr	.33	.95	.96	.84			Tr	.34	.95	.96	–
Un	.33	.99	.95	.97	.84		Un	.34	.99	.95	.97	–
Pe	.21	.88	.95	.88	.87	.76	Pe	.21	.89	.96	.89	.88	–