“Let me explain!”: exploring the potential of virtual agents in explainable AI interaction design
|
Neural Network
|
Speech Recognition
|
Natural Language Processing
|
Generic
|
Audio, Text, Visual
|
Features Importance, Other
|
Controlled experiment
|
Helpfulness, Satistfaction, Trust, Understandability, Visual appeal
|
“That's (not) the output I expected!”On the role of end user expectations in creating explanations of AI systems
|
Probabilistic
|
Text Classification
|
Media and Communication
|
Generic
|
Text, Visual
|
Counter-exemplars/factual, Features Importance
|
Controlled experiment
|
Satistfaction, Understandability, Usefulness
|
A Big Bang-Big Crunch Type-2 Fuzzy Logic System for Explainable Predictive Maintenance
|
Fuzzy
|
Estimation
|
Other
|
Domain-experts
|
Text, Visual
|
Decision Rules
|
|
|
A Clinical Decision Support System for Sleep Staging Tasks with Explanations from Artificial Intelligence: User-Centered Design and Evaluation Study
|
Neural Network
|
Multi-class Classification
|
Health
|
Domain-experts
|
Visual
|
Neurons Activation, Salient Mask
|
Interview, User observation
|
Helpfulness, Intuitiveness
|
A process framework for inducing and explaining Datalog theories
|
White Box
|
Image Classification
|
Artificial Intelligence and Robotics Systems, Health
|
|
Natural Language, Text, Visual
|
Decision Rules
|
|
|
A qualitative research framework for the design of user-centered displays of explanations for machine learning model predictions in healthcare
|
Ensemble
|
Binary classification
|
Health
|
Domain-experts
|
Visual
|
Shapley Values
|
Focus Group
|
|
A User Interface for Explaining Machine Learning Model Explanations
|
Neural Network
|
Image Classification
|
General
|
AI experts
|
Visual
|
Salient Mask
|
|
|
A Visual Analytics Framework for Contrastive Network Analysis
|
Neural Network
|
Embedding
|
Network
|
AI experts
|
Visual
|
Counter-exemplars/factual, Features Importance
|
Controlled experiment
|
Learnability, Task performance, Usability, Workload
|
A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations
|
Neural Network
|
Binary classification
|
General, Health
|
AI experts, Domain-experts
|
Visual
|
Counter-exemplars/factual, Decision Rules, Features Importance
|
|
|
AI-Driven User Interface Design for Solving a Rubik’s Cube: A Scaffolding Design Perspective
|
Unknown
|
Multi-class Classification
|
Media and Communication
|
Domain-experts, Non-experts
|
Natural Language, Text, Visual
|
None
|
Usability study
|
Usability
|
AIMEE: An Exploratory Study of How Rules Support AI Developers to Explain and Edit Models
|
Rule-Based
|
Binary classification
|
Artificial Intelligence and Robotics Systems
|
AI experts
|
Text, Visual
|
Decision Rules
|
Controlled experiment, Interview, User observation
|
Ease of use, Satistfaction, Task performance, Usefulness, Workload
|
ALEEDSA: Augmented Reality for Interactive Machine Learning
|
|
Regression
|
Finance/Economics
|
Domain-experts
|
Visual
|
Counter-exemplars/factual
|
Interactive feedback session
|
Usefulness
|
Algorithmic and HCI Aspects for Explaining Recommendations of Artistic Images
|
Math, Neural Network
|
Embedding, Recommendation
|
Finance/Economics, Media and Communication
|
Generic
|
Text, Visual
|
Exemplars, Features Importance
|
Controlled experiment
|
Recommendation Efficacy, Workload
|
AlphaDAPR: An AI-Based Explainable Expert Support System for Art Therapy
|
Neural Network
|
Image Classification, Object detection
|
Artificial Intelligence and Robotics Systems, Health, Media and Communication
|
Domain-experts
|
Text, Visual
|
Exemplars
|
Interview, Usability study
|
Ease of use, Explainability, Familiarity, Satistfaction, Trust, Understandability, Willing to reuse
|
An Empirical Study of Reward Explanations With Human-Robot Interaction Applications
|
|
|
Artificial Intelligence and Robotics Systems
|
Generic
|
Text, Visual
|
Exemplars, Features Importance
|
Controlled experiment
|
Perceived quality, Predictability, Workload
|
An explanation space to align user studies with the technical development of Explainable AI
|
|
|
None
|
|
|
None
|
|
|
An Explanation User Interface for a Knowledge Graph-Based XAI Approach to Process Analysis
|
Unknown
|
Recommendation
|
Finance/Economics
|
Domain-experts
|
Text
|
Exemplars, Features Importance
|
Interview
|
UX, Usability
|
Analyzing Description, User Understanding and Expectations of AI in Mobile Health Applications
|
|
|
Health
|
|
|
None
|
|
|
Assessing the communication gap between AI models and healthcare professionals: Explainability, utility and trust in AI-driven clinical decision-making
|
Ensemble
|
Regression
|
Health
|
Domain-experts
|
Text, Visual
|
Shapley Values
|
Controlled experiment
|
Ease of use, Satistfaction, Trust, Understandability
|
Building Trust in Interactive Machine Learning via User Contributed Interpretable Rules
|
White Box
|
Binary classification
|
Media and Communication
|
Generic
|
Text, Visual
|
Decision Rules
|
Controlled experiment
|
Ease of use, Perceived control, Perceived quality, Satistfaction, Trust, Understandability
|
C-XAI: A conceptual framework for designing XAI tools that support trust calibration
|
|
|
|
|
|
|
|
|
ChatrEx: Designing Explainable Chatbot Interfaces for Enhancing Usefulness, Transparency, and Trust
|
Unknown
|
Multi-class Classification
|
Natural Language Processing
|
Generic
|
Visual
|
Exemplars
|
Controlled experiment, Usability study
|
Explainability, Transparency, Trust, Usability, Usefulness
|
CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization
|
Neural Network
|
Image Classification
|
Education, Health
|
Non-experts
|
Text, Visual
|
None
|
Interview, Survey, User observation
|
Usability, Usefulness
|
Co-Design and Evaluation of an Intelligent Decision Support System for Stroke Rehabilitation Assessment
|
Neural Network, White Box
|
Binary classification
|
Health
|
Domain-experts
|
Text, Video, Visual
|
Features Importance
|
Controlled experiment
|
Trust, Usefulness, Willing to reuse, Workload
|
Co-Design of Human-Centered, Explainable AI for Clinical Decision Support
|
Unknown
|
Binary classification
|
Health
|
Domain-experts
|
Text, Visual
|
Decision Rules
|
Survey
|
Trust
|
ConceptExplainer: Interactive Explanation for Deep Neural Networks from a Concept Perspective
|
Neural Network
|
Image Classification
|
General
|
Non-experts
|
Text, Visual
|
Exemplars
|
Controlled experiment, User observation
|
Usability, Usefulness
|
Contextualization and Exploration of Local Feature Importance Explanations to Improve Understanding and Satisfaction of Non-Expert Users
|
Math
|
Regression
|
Finance/Economics
|
Non-experts
|
Text, Visual
|
Exemplars, Shapley Values
|
Controlled experiment
|
Satistfaction, Understandability
|
Contextualizing the Why: The Potential of Using Visual Map As a Novel XAI Method for Users with Low AI-literacy
|
Unknown
|
Binary classification
|
None
|
AI experts, Non-experts
|
Visual
|
Counter-exemplars/factual, Decision Tree, Shapley Values
|
Controlled experiment
|
Cognitive Load, Explainability, Satistfaction
|
ConvXAI : Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing
|
Neural Network
|
Recommendation
|
Education
|
Non-experts
|
Natural Language, Text
|
Counter-exemplars/factual, Exemplars, Salient Mask
|
Controlled experiment
|
Cognitive Load, Perceived control, Perceived efficiency, Understandability
|
ConvXAI: a System for Multimodal Interaction with Any Black-box Explainer
|
Ensemble, Probabilistic, White Box
|
Binary classification, Multi-class Classification, Regression
|
General
|
AI experts, Domain-experts, Non-experts
|
Natural Language, Text, Visual
|
Counter-exemplars/factual, Features Importance, Shapley Values
|
Controlled experiment
|
Explainability, Perceived quality, Usefulness
|
DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models
|
Agnostic
|
Agnostic
|
General
|
AI experts, Non-experts
|
Visual
|
Counter-exemplars/factual
|
Interview
|
Usability
|
DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction
|
Neural Network
|
Text Classification
|
Natural Language Processing
|
Domain-experts
|
Text, Visual
|
Neurons Activation
|
Controlled experiment
|
Task performance, Workload
|
DeepVix: Explaining Long Short-Term Memory Network with High Dimensional Time Series Data
|
Neural Network
|
Agnostic
|
General
|
|
Visual
|
Neurons Activation
|
|
|
Design and Evaluation of Trustworthy Knowledge Tracing Model for Intelligent Tutoring System
|
Neural Network
|
Estimation
|
Education
|
Domain-experts, Non-experts
|
Text, Visual
|
Shapley Values
|
Controlled experiment, Interview
|
Trust, Understandability
|
Designing an XAI interface for BCI experts: A contextual design for pragmatic explanation interface based on domain knowledge in a specific context
|
Neural Network
|
Image Classification
|
Health
|
Domain-experts
|
Text, Visual
|
Shapley Values
|
Controlled experiment, Interview, User observation
|
Explanation quality, Usability
|
Designing and Evaluating Explanations for a Predictive Health Dashboard: A User-Centred Case Study
|
Unknown
|
Recommendation
|
Health
|
Domain-experts
|
Text, Visual
|
Counter-exemplars/factual, Features Importance
|
Focus Group
|
Usability
|
Designing for Confidence: The Impact of Visualizing Artificial Intelligence Decisions
|
Neural Network
|
Image Classification
|
General
|
AI experts
|
Visual
|
Salient Mask
|
Controlled experiment
|
Confidence, Trust, Workload
|
Designing Theory-Driven User-Centric Explainable AI
|
Ensemble
|
Multi-class Classification
|
Health
|
Domain-experts
|
Text, Visual
|
Decision Rules, Sensitivity Analysis, Shapley Values
|
Co-design
|
|
DETOXER: A Visual Debugging Tool With Multiscope Explanations for Temporal Multilabel Classification
|
Neural Network, Probabilistic
|
Object detection
|
Artificial Intelligence and Robotics Systems
|
Domain-experts
|
Visual
|
|
User observation
|
Helpfulness, Perceived quality
|
Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations
|
White Box
|
Regression
|
Health
|
Domain-experts, Non-experts
|
Text, Visual
|
Counter-exemplars/factual, Shapley Values
|
Interview, Usability study
|
Actionability, Trust, Understandability, Usefulness
|
DMT-EV: An Explainable Deep Network for Dimension Reduction
|
Neural Network
|
Dimensionality Reduction
|
General
|
Domain-experts
|
Visual
|
Salient Mask
|
Interview, Usability study
|
|
Does This Explanation Help? Designing Local Model-Agnostic Explanation Representations and an Experimental Evaluation Using Eye-Tracking Technology
|
Neural Network
|
Estimation
|
Finance/Economics
|
AI experts, Non-experts
|
Text, Visual
|
Decision Rules, Features Importance, Shapley Values
|
Co-design, Controlled experiment
|
Forward-prediction score, Satistfaction, Trust, Understandability, Usefulness
|
Editable machine learning models? A rule-based framework for user studies of explainability
|
White Box
|
Multi-class Classification
|
Artificial Intelligence and Robotics Systems
|
|
Text
|
Decision Rules
|
|
|
Effects of Explanations in AI-Assisted Decision Making: Principles and Comparisons
|
|
|
None
|
|
|
None
|
|
|
Effects of Interactivity and Presentation on Review-Based Explanations for Recommendations
|
Neural Network
|
Text Classification
|
Natural Language Processing
|
Non-experts
|
Text, Visual
|
Features Importance
|
Controlled experiment
|
Explanation quality, Persuasiveness, Transparency, Trust
|
Elements that Influence Transparency in Artificial Intelligent Systems - A Survey
|
|
|
|
|
|
|
|
|
ELVIRA: An explainable agent for value and utility-driven multiuser privacy
|
|
|
Other
|
Generic
|
|
Counter-exemplars/factual
|
Controlled experiment
|
Recommendation Efficacy, Satistfaction, Value Adherence (measured with PVQ)
|
Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study
|
Neural Network
|
Image Classification
|
General
|
Generic
|
Text, Visual
|
Salient Mask
|
Controlled experiment
|
Forward-prediction score
|
Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling
|
Neural Network
|
Image Classification
|
Health
|
|
Visual
|
Decision Rules
|
|
|
EXMOS: Explanatory Model Steering through Multifaceted Explanations and Data Configurations
|
Ensemble
|
Binary classification
|
Health
|
Domain-experts
|
Visual
|
Decision Rules, Features Importance, Shapley Values
|
Controlled experiment, Interview
|
Cognitive Load, Model effectiveness, Trust, Understandability
|
ExplAIn Yourself! Transparency for Positive UX in Autonomous Driving
|
None
|
Image Classification
|
Mobility
|
Non-experts
|
Audio
|
None
|
Controlled experiment
|
Perceived Safety, Perceived control, Technology acceptance, UX
|
Explainability via Interactivity? Supporting Nonexperts’Sensemaking of Pre-Trained CNN by Interacting with Their Daily Surroundings
|
Neural Network
|
Image Classification
|
Education
|
Non-experts
|
Visual
|
Salient Mask
|
Interview
|
|
Explainable AI for Non-Experts: Energy Tariff Forecasting
|
Ensemble
|
Regression
|
Finance/Economics
|
Non-experts
|
Visual
|
Counter-exemplars/factual, Shapley Values
|
|
|
Explainable AI-Based Interface System for Weather Forecasting Model
|
Neural Network
|
Multi-class Classification
|
Agriculture and Nature
|
Domain-experts
|
Text, Visual
|
Features Importance, Salient Mask
|
Focus Group, Interview
|
Trust, Understandability, Usefulness
|
Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach
|
White Box
|
Multi-class Classification
|
Health
|
Domain-experts
|
Visual
|
Counter-exemplars/factual, Exemplars
|
Usability study
|
Confidence
|
Explainable Artificial Intelligence for Cytological Image Analysis
|
Neural Network
|
Multi-class Classification
|
Health
|
AI experts, Domain-experts
|
Visual
|
Features Importance
|
Controlled experiment
|
Bias Detection, Trust, Understandability
|
Explainable artificial intelligence for education and training
|
|
|
|
|
|
|
|
|
Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities
|
|
|
None
|
|
|
None
|
|
|
Explainable Visualization for Interactive Exploration of CNN on Wikipedia Vandal Detection
|
Neural Network
|
Binary classification
|
Other
|
|
Visual
|
Other
|
No study
|
|
ExplainExplore: Visual Exploration of Machine Learning Explanations
|
Agnostic
|
Multi-class Classification
|
General
|
AI experts
|
Visual
|
Features Importance
|
Usability study
|
|
Explaining Artificial Intelligence with Tailored Interactive Visualisations
|
|
|
Education, Health, Other
|
|
|
None
|
|
|
Explaining Recommendations through Conversations: Dialog Model and the Effects of Interface Type and Degree of Interactivity
|
Math, Neural Network
|
Recommendation, Sentiment Analysis
|
Natural Language Processing
|
Generic
|
Natural Language
|
Other
|
Wizard-of-Oz
|
Confidence, Perceived effectiveness, Transparency
|
Explaining User Models with Different Levels of Detail for Transparent Recommendation: A User Study
|
Math
|
Recommendation
|
Recommendation
|
Generic
|
Text, Visual
|
None
|
Controlled experiment
|
Familiarity, Level of domain knowledge, Need for cognition, Perceived effectiveness, Perceived efficiency, Personal innovativeness, Persuasiveness, Satistfaction, Scrutability, Task performance, Technical expertise, Transparency, Trust, Trust propensity (of user)
|
Exploring the Impact of Explainability on Trust and Acceptance of Conversational Agents ‚ A Wizard of Oz Study
|
Neural Network, Rule-Based
|
Recommendation
|
Natural Language Processing
|
Generic
|
Natural Language
|
Exemplars
|
Wizard-of-Oz
|
Ease of use, Technology acceptance, Trust, Understandability, Usefulness
|
Exploring the Usability and Trustworthiness of AI-Driven User Interfaces for Neurological Diagnosis
|
Unknown
|
Image Classification
|
Health
|
Domain-experts
|
Visual
|
Counter-exemplars/factual, Shapley Values
|
Survey
|
Perceived effectiveness, Satistfaction, Trust, Understandability
|
Finding AI’s Faults with AAR/AI: An Empirical Study
|
Reinforcement Learning
|
Regression
|
Media and Communication
|
Domain-experts
|
Text, Visual
|
Decision Tree
|
Controlled experiment
|
Task performance, Workload
|
From explainable to interactive AI: A literature review on current trends in human-AI interaction
|
|
|
|
|
|
|
|
|
From Philosophy to Interfaces: An Explanatory Method and a Tool Inspired by Achinstein’s Theory of Explanation
|
Neural Network
|
Binary classification
|
Finance/Economics
|
Generic
|
Text
|
Counter-exemplars/factual
|
Controlled experiment
|
Perceived effectiveness, Perceived efficiency, Satistfaction
|
Gamut: A Design Probe to Understand How Data Scientists Understand Machine Learning Models
|
White Box
|
Binary classification, Regression
|
Finance/Economics, General, Health
|
AI experts
|
Text, Visual
|
Counter-exemplars/factual, Exemplars, Features Importance
|
Usability study
|
Usability
|
Generating and Visualizing Trace Link Explanations
|
|
|
Artificial Intelligence and Robotics Systems
|
Domain-experts
|
Text, Visual
|
Exemplars
|
Co-design, Controlled experiment
|
Explanation helpfulness, Helpfulness
|
Giving DIAnA More TIME –Guidance for the Design of XAI-Based Medical Decision Support Systems
|
|
|
None
|
|
|
None
|
|
|
GUI Design Patterns for Improving the HCI in Explainable Artificial Intelligence
|
|
|
None
|
|
|
None
|
|
|
Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction"
|
Unknown
|
Image Classification
|
Other
|
AI experts, Domain-experts
|
Visual
|
None
|
Interactive feedback session, Interview, Survey
|
Needs for explainability (XAI Question Bank)
|
How do visual explanations foster end users' appropriate trust in machine learning?
|
Other Black-Box
|
Image Classification
|
Other
|
AI experts, Non-experts
|
Visual
|
Exemplars
|
Controlled experiment
|
|
How the different explanation classes impact trust calibration: The case of clinical decision support systems
|
None
|
Binary classification
|
Health
|
Domain-experts
|
Text, Visual
|
Counter-exemplars/factual, Exemplars, Features Importance
|
Controlled experiment, Interview
|
Trust
|
How to explain AI systems to end users: a systematic literature review and research agenda
|
|
|
None
|
|
|
None
|
|
|
Human-XAI Interaction: A Review and Design Principles for Explanation User Interfaces
|
|
|
None
|
|
|
None
|
|
|
I Think I Get Your Point, AI! The Illusion of Explanatory Depth in Explainable AI
|
Ensemble
|
Regression
|
Finance/Economics
|
Non-experts
|
Text, Visual
|
Shapley Values
|
User observation
|
Perceived understanding
|
If it is easy to understand, then it will have value‚ : Examining Perceptions of Explainable AI with Community Health Workers in Rural India
|
Unknown
|
Binary classification
|
Health
|
Domain-experts
|
Visual
|
Features Importance, Shapley Values
|
Interview, User observation
|
Perceived quality, Understandability
|
Impact of example-based XAI for neural networks on trust, understanding, and performance
|
Neural Network
|
Image Classification
|
Health
|
AI experts
|
Visual
|
Exemplars
|
Controlled experiment
|
Explainability, Fairness rating, Trust, Understandability
|
Initial results on personalizing explanations of AI hints in an ITS
|
Unknown
|
Constraint's satisfaction problem
|
Education
|
Domain-experts
|
Text, Visual
|
None
|
Controlled experiment
|
Intrusiveness, Trust, Understandability, Usefulness
|
Interactive Explainable Case-Based Reasoning for Behavior Modelling in Videogames
|
Other
|
Behaviour Learning
|
Media and Communication
|
Domain-experts
|
Visual
|
Exemplars
|
User observation
|
Explanation helpfulness, Intuitiveness, Perceived effectiveness, Perceived understanding, Predictability, Technology acceptance
|
Interactive Explanation with Varying Level of Details in an Explainable Scientific Literature Recommender System
|
Neural Network
|
Recommendation
|
Education
|
Non-experts
|
Text, Visual
|
Other
|
Interactive feedback session, Interview
|
Cognitive Load, Explanation helpfulness, Perceived control, Perceived quality, Satistfaction, Transparency, Trust, Usability
|
Interfaces for Explanations in Human-AI Interaction: Proposing a Design Evaluation Approach
|
Unknown
|
Multi-class Classification
|
Education
|
Generic
|
Text, Visual
|
Features Importance
|
Controlled experiment
|
Advice adherence of users
|
Investigating the importance of first impressions and explainable AI with interactive video analysis
|
Neural Network
|
Image Classification
|
Other
|
Generic
|
Text
|
Neurons Activation
|
Controlled experiment
|
Confidence, Explanation helpfulness, Perceived effectiveness, Task performance
|
Investigating the Intelligibility of Plural Counterfactual Examples for Non-Expert Users: An Explanation User Interface Proposition and User Study
|
Ensemble
|
Binary classification
|
Finance/Economics
|
Non-experts
|
Text, Visual
|
Counter-exemplars/factual
|
Controlled experiment
|
Satistfaction, Understandability
|
Investigating the understandability of XAI methods for enhanced user experience: When Bayesian network users became detectives
|
Probabilistic
|
Estimation
|
Other
|
Non-experts
|
Text, Visual
|
None
|
Survey
|
Perceived effectiveness, Plausibility, Understandability
|
LIMEADE: From AI Explanations to Advice Taking
|
Neural Network
|
Text Classification
|
Recommendation
|
Domain-experts
|
Text
|
Features Importance
|
User observation
|
Intuitiveness, Perceived control, Perceived effectiveness, Perceived quality, Transparency, Trust
|
M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis
|
Neural Network
|
Multimodal Classification
|
Natural Language Processing
|
Domain-experts
|
Visual
|
Decision Tree, Features Importance, Shapley Values
|
Interview
|
Usability
|
Making SHAP Rap: Bridging Local and Global Insights Through Interaction and Narratives
|
Ensemble
|
Binary classification
|
Finance/Economics
|
Non-experts
|
Text, Visual
|
Shapley Values
|
Usability study
|
Explainability, Understandability
|
Meaningful Explanation Effect on User‚ Trust in an AI Medical System: Designing Explanations for Non-Expert Users
|
Unknown
|
Estimation
|
Health
|
Domain-experts, Non-experts
|
Text, Visual
|
Salient Mask
|
Controlled experiment, Interview
|
Trust
|
Mental Models of Mere Mortals with Explanations of Reinforcement Learning
|
Reinforcement Learning
|
Multi-class Classification
|
Media and Communication
|
Domain-experts, Non-experts
|
Visual
|
Salient Mask
|
Usability study
|
Perceived understanding, Workload
|
On Selective, Mutable and Dialogic XAI: A Review of What Users Say about Different Types of Interactive Explanations
|
|
|
None
|
|
|
None
|
|
|
On the Importance of User Backgrounds and Impressions: Lessons Learned from Interactive AI Applications
|
Neural Network
|
Object detection
|
Other
|
Generic
|
Visual
|
Other
|
Controlled experiment
|
Frequency of usage, Helpfulness, Perceived effectiveness
|
Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Exploration
|
Neural Network
|
Binary classification
|
Finance/Economics
|
Non-experts
|
Text
|
Counter-exemplars/factual
|
Controlled experiment
|
Usability
|
QuestionComb: A Gamification Approach for the Visual Explanation of Linguistic Phenomena through Interactive Labeling
|
Rule-Based
|
Text Classification
|
Natural Language Processing
|
Domain-experts
|
Visual
|
Decision Rules
|
Usability study
|
Perceived effectiveness, Transparency, Usability, Usefulness
|
Questioning the ability of feature-based explanations to empower non-experts in robo-advised financial decision-making
|
Rule-Based
|
Recommendation
|
Finance/Economics
|
Non-experts
|
Text, Visual
|
Features Importance
|
Controlled experiment, Interview
|
Cognitive Load, Engagement, Reliance on AI, Trust, Understandability
|
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
|
|
|
None
|
|
|
None
|
|
|
RADAR-X: An Interactive Mixed Initiative Planning Interface Pairing Contrastive Explanations and Revised Plan Suggestions
|
|
|
Other
|
Domain-experts
|
Natural Language, Text
|
Counter-exemplars/factual
|
|
|
Rapid Assisted Visual Search: Supporting Digital Pathologists with Imperfect AI
|
Neural Network
|
Image Classification
|
Health
|
Domain-experts
|
Text, Visual
|
Other
|
Interview
|
Model effectiveness, Task performance
|
Reinforcement Learning over Sentiment-Augmented Knowledge Graphs towards Accurate and Explainable Recommendation
|
Reinforcement Learning
|
Recommendation
|
Recommendation
|
Non-experts
|
Text
|
Other
|
Survey
|
Informativeness (ResQue questionnaire), Persuasiveness, Transparency, Trust, Usability
|
Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis
|
Neural Network
|
Estimation
|
Health
|
Domain-experts
|
Text, Visual
|
Counter-exemplars/factual, Features Importance
|
Interview, UI inspection
|
Usability
|
RuleMatrix: Visualizing and Understanding Classifiers with Rules
|
Neural Network
|
Multi-class Classification
|
General
|
Non-experts
|
Visual
|
Decision Rules
|
Usability study
|
Usability
|
Sand-in-the-Loop: Investigating Embodied Co-Creation for Shared Understandings of Generative AI
|
|
|
None
|
Domain-experts
|
Tangible
|
Other
|
Controlled experiment
|
Learnability, Predictability, Satistfaction, Usability, Workload
|
Self-Explaining Abilities of an Intelligent Agent for Transparency in a Collaborative Driving Context
|
Reinforcement Learning
|
Estimation
|
Artificial Intelligence and Robotics Systems, Media and Communication
|
Domain-experts
|
Text, Visual
|
Decision Tree
|
User observation
|
Task performance, Workload
|
Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making
|
Unknown
|
Regression
|
Other
|
Domain-experts
|
Text, Visual
|
Shapley Values
|
Controlled experiment, Interview, User observation
|
Confidence, Helpfulness, Trust
|
Slide to Explore 'What If': An Analysis of Explainable Interfaces
|
|
|
|
|
|
|
|
|
Supporting Exploratory Search with a Visual User-Driven Approach
|
Math
|
Recommendation
|
Recommendation
|
Non-experts
|
Visual
|
None
|
Controlled experiment, User observation
|
Task performance, Usability, Workload
|
Supporting High-Uncertainty Decisions through AI and Logic-Style Explanations
|
Ensemble
|
Binary classification
|
Finance/Economics
|
Generic
|
Visual
|
Counter-exemplars/factual, Exemplars, Other, Shapley Values
|
Controlled experiment
|
Perceived effectiveness, Reliance on AI, Task performance
|
Tangible Explainable AI-an Initial Conceptual Framework
|
|
|
Health
|
|
Tangible
|
Counter-exemplars/factual, Decision Rules, Partial Dependency Plot, Shapley Values
|
|
|
The Flow of Trust: A Visualization Framework to Externalize, Explore, and Explain Trust in ML Applications
|
|
|
None
|
|
|
None
|
|
|
The grammar of interactive explanatory model analysis
|
Ensemble
|
Binary classification
|
Artificial Intelligence and Robotics Systems, Health
|
AI experts
|
Visual
|
Partial Dependency Plot, Shapley Values
|
Survey
|
Confidence, Explanation helpfulness, Perceived effectiveness
|
The Situation Awareness Framework for Explainable AI (SAFE-AI) and Human Factors Considerations for XAI Systems
|
|
|
None
|
|
|
None
|
|
|
The Use of Responsible Artificial Intelligence Techniques in the Context of Loan Approval Processes
|
Ensemble, Probabilistic, White Box
|
Binary classification
|
Finance/Economics
|
AI experts, Domain-experts
|
Text, Visual
|
Shapley Values
|
Controlled experiment, Interview
|
Explanation quality, Fairness rating, Perceived effectiveness, Reliance on AI, Trust, Usability
|
TimeTuner: Diagnosing Time Representations for Time-Series Forecasting with Counterfactual Explanations
|
Neural Network
|
Estimation
|
General
|
AI experts
|
Visual
|
Counter-exemplars/factual
|
Interview, UI inspection
|
Usability
|
Toward Involving End-Users in Interactive Human-in-the-Loop AI Fairness
|
White Box
|
Regression
|
Finance/Economics
|
Generic, Non-experts
|
Text, Visual
|
Exemplars
|
Co-design, User observation
|
Fairness rating, Workload
|
Towards Human-Centered Explainable AI: A Survey of User Studies for Model Explanations
|
|
|
|
|
|
|
|
|
Towards Sonification in Multimodal and User-FriendlyExplainable Artificial Intelligence
|
|
Agnostic
|
General
|
|
Audio
|
Counter-exemplars/factual, Exemplars, Neurons Activation
|
|
|
TRIVEA: Transparent Ranking Interpretation using Visual Explanation of black-box Algorithmic rankers
|
Other
|
Ranking
|
Education
|
AI experts
|
Visual
|
Features Importance, Partial Dependency Plot
|
Survey
|
Usability
|
Unraveling ML Models of Emotion With NOVA: Multi-Level Explainable AI for Non-Experts
|
Neural Network
|
Image Classification
|
Natural Language Processing
|
Non-experts
|
Visual
|
Features Importance
|
Controlled experiment
|
Computer Self-Efficacy, Trust, Workload
|
User Characteristics in Explainable AI: The Rabbit Hole of Personalization?
|
Neural Network
|
Binary classification
|
Media and Communication, Natural Language Processing
|
Generic
|
Text, Visual
|
Features Importance
|
Controlled experiment
|
Perceived understanding, Personality, Trust, Understandability
|
User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review
|
|
|
|
|
|
|
|
|
VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networks
|
Neural Network
|
Image Classification
|
Network
|
AI experts
|
Visual
|
Salient Mask
|
Controlled experiment
|
Ease of use, Helpfulness, Task performance
|
VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models
|
Ensemble, Probabilistic
|
Multi-class Classification
|
Health
|
Domain-experts
|
Visual
|
Shapley Values
|
Interview, User observation
|
|
Video-based AI Decision Support System for Lifting Risk Assessment
|
White Box
|
Image Classification
|
Health
|
Domain-experts, Non-experts
|
Text, Visual
|
Shapley Values
|
Survey
|
Confidence, Task performance
|
VIME: Visual Interactive Model Explorer for Identifying Capabilities and Limitations of Machine Learning Models for Sequential Decision-Making
|
Probabilistic
|
Binary classification
|
Mobility
|
AI experts
|
Visual
|
Other
|
User observation
|
Usability
|
VISHIEN-MAAT: Scrollytelling visualization design for explaining Siamese Neural Network concept to non-technical users
|
Neural Network
|
Estimation
|
General
|
Domain-experts
|
Visual
|
Other
|
Focus Group
|
Understandability
|
Visual Analytics for Exploring Air Quality Data in an AI-Enhanced IoT Environment
|
Ensemble
|
Regression
|
Other
|
|
Visual
|
Shapley Values
|
|
|
Visual Analytics for Human-Centered Machine Learning
|
|
|
None
|
|
|
None
|
|
|
Visual Exploration of Machine Learning Model Behavior with Hierarchical Surrogate Rule Sets
|
Rule-Based
|
Agnostic
|
General
|
Domain-experts
|
Visual
|
None
|
Usability study, User observation
|
Task performance, Workload
|
Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
|
Neural Network
|
Estimation
|
Natural Language Processing
|
|
Text, Visual
|
Counter-exemplars/factual
|
No study
|
|
Visual, Textual or Hybrid: The Effect of User Expertise on Different Explanations
|
Agnostic
|
Regression
|
Other
|
AI experts, Non-experts
|
Text, Visual
|
Counter-exemplars/factual, Features Importance, Partial Dependency Plot
|
Controlled experiment
|
Task performance, Understandability, Usability
|
VMS: Interactive Visualization to Support the Sensemaking and Selection of Predictive Models
|
Ensemble, Neural Network, White Box
|
Regression
|
Health
|
Non-experts
|
Visual
|
Features Importance, Shapley Values
|
Controlled experiment, User observation
|
Perceived effectiveness, Satistfaction, Understandability
|
What Are People Doing About XAI User Experience? A Survey on AI Explainability Research and Practice
|
|
|
None
|
|
|
None
|
|
|
What Is the Focus of XAI in UI Design? Prioritizing UI Design Principles for Enhancing XAI User Experience
|
Unknown
|
Multi-class Classification
|
Health
|
Non-experts
|
Natural Language
|
Features Importance
|
Controlled experiment, Interview
|
Perceived efficiency, Persuasiveness, Satistfaction, Trust, Understandability
|
What’s on Your Mind, NICO?: XHRI: A Framework for eXplainable Human-Robot Interaction
|
Neural Network
|
Image Classification
|
Artificial Intelligence and Robotics Systems
|
|
Natural Language, Non-verbal Explanation, Verbal Explanation, Visual
|
None
|
|
|
Where Are We and Where Can We Go on the Road to Reliance-Aware Explainable User Interfaces?
|
|
|
|
|
|
|
|
|
Why? Why not? When? Visual Explanations of Agent Behaviour in Reinforcement Learning
|
Neural Network, Reinforcement Learning
|
Behaviour Learning
|
Artificial Intelligence and Robotics Systems, Health
|
Non-experts
|
Text, Visual
|
Features Importance
|
Usability study
|
Understandability
|
XAI for Learning: Narrowing down the Digital Divide between “new”and “old”Experts
|
|
|
None
|
|
|
None
|
|
|
XAIT: An Interactive Website for Explainable AI for Text
|
|
Text Classification
|
Natural Language Processing
|
|
|
|
Interview
|
|
XDesign: Integrating Interface Design into Explainable AI Education
|
Neural Network
|
Image Classification
|
Education
|
AI experts
|
Text, Visual
|
Features Importance
|
Usability study
|
|
XplainScreen: Unveiling the Black Box of Graph Neural Network Drug Screening Models with a Unified XAI Framework
|
Neural Network
|
Estimation
|
Health
|
Domain-experts
|
Text, Visual
|
Neurons Activation, Salient Mask
|
Interactive feedback session
|
Usefulness
|