Artificial Intelligence in HCI

Name: Artificial Intelligence in HCI | 3rd International Conference, AI-HCI 2022, Held as Part of the 24th HCI International Conference, HCII 2022, Virtual Event, June 26 - July 1, 2022, Proceedings
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

3rd International Conference, AI-HCI 2022, Held as Part of the 24th HCI International Conference, HCII 2022, Virtual Event, June 26 - July 1, 2022, Proceedings

Helmut Degen Stavroula Ntoa(Herausgeber*in)

Springer (Verlag)

Erschienen am 14. Mai 2022

XXIII, 612 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-031-05643-7 (ISBN)

96,29 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Foreword
HCI International 2022 Thematic Areas and Affiliated Conferences
List of Conference Proceedings Volumes Appearing Before the Conference
Preface
3rd International Conference on Artificial Intelligence in HCI (AI-HCI 2022)
HCI International 2023
Contents
Human-Centered AI
Exploring the Design Context of AI-Powered Services: A Qualitative Investigation of Designers' Experiences with Machine Learning
1 Introduction
2 Literature Review
2.1 UX Design Practice and the Concept of a Design Material
2.2 Machine Learning as a Design Material
3 Method
3.1 Empirical Data Collection
3.2 Thematic Analysis
4 Findings
4.1 Absence of Competence
4.2 Lack of Incentive for Competence Development
4.3 Challenges Articulating Design Criteria
4.4 Mature Versus Immature Clients
4.5 Lack of Support for Ethical Concerns
4.6 Concluding Remarks
5 Discussion
6 Conclusion
References
Measuring and Predicting Human Trust in Recommendations from an AI Teammate
1 Trust in AI Teammates
2 Experimental Paradigm
3 Measures
4 Results
5 Discussion
6 Conclusion
References
Promoting Human Competences by Appropriate Modes of Interaction for Human-Centered-AI
1 Introduction
2 Methodological Approach
3 Interaction Modes
3.1 Offering Explanations and Possibilities for Exploration
3.2 Testing
3.3 Initiating and Performing Re-training
3.4 Variation of Underlying Data Sets and Methods
3.5 Flexible Sequencing or Filtering of Data Input
3.6 Identification and Comparison of Similar Cases
3.7 Refinement
3.8 Intervention
3.9 Vetoing
3.10 Critiquing
4 Conclusion and Outlook
References
Artificial Intelligence Augmenting Human Teams. A Systematic Literature Review on the Opportunities and Concerns
1 Introduction
2 Methods
2.1 Planning the Literature Review
3 Findings
4 Discussion and Recommendation
5 Implications for Research and Practice
6 Conclusion and Limitations
References
Adoption and Perception of Artificial Intelligence Technologies by Children and Teens in Education
1 Introduction
2 Previous Work
3 Methodology
3.1 Keyword Search
3.2 Screening the Titles and Abstracts
3.3 Screening the Full Text
4 Results
5 Discussion
6 Conclusions
References
Analysis of the Impact of Applying UX Guidelines to Reduce Noise and Focus Attention
1 Introduction
2 Proposal and Methodology
3 Results and Evaluation
4 Conclusions
References
Gamifying the Human-in-the-Loop: Toward Increased Motivation for Training AI in Customer Service
1 Introduction
2 Related Work
3 Research Approach
4 Objectives of a Solution
5 Artifact Design and Development
6 Demonstration
7 Evaluation
8 Discussion and Conclusion
References
Explainable and Trustworthy AI
Dominant View and Perception of Artificial Intelligence in Developing Economy
1 Introduction
2 Method
2.1 Participants
2.2 Instruments
3 Results
3.1 AI Powers African Economic Development
3.2 AI Systems Create More Jobs Than They Eliminate
3.3 Support for AI System Development
3.4 AI Induce Algorithmic Colonialism
3.5 Openness of AI Operation
3.6 African Readiness to Adopt AI
4 Discussion
5 Conclusion
References
MoReXAI - A Model to Reason About the eXplanation Design in AI Systems
1 Introduction
2 Foundations and Related Works
2.1 Ethical Principles and Explainable Artificial Intelligence (XAI)
2.2 Semiotic Engineering
2.3 Related Works
3 The Model for Reasoning About AI Explanation Design
3.1 Model Questions
3.2 MoReXAI Structure
3.3 MoReXai Use
4 Case Study
4.1 Case Study Planning
4.2 Model Application
4.3 Results: Talking About Explanations
5 Discussion
5.1 About the Epistemic Character of the MoReXAI
5.2 Improvements to the MoReXAI
6 Conclusão
References
(De)Coding Social Practice in the Field of XAI: Towards a Co-constructive Framework of Explanations and Understanding Between Lay Users and Algorithmic Systems
1 Introduction
2 Method
3 Discussion/Empirical Insights
4 Conclusion
References
Explainable AI for Suicide Risk Assessment Using Eye Activities and Head Gestures
1 Introduction
2 Background
3 Methodology
3.1 Suicide Dataset Collection
3.2 Feature Extraction
3.3 Feature Selection
3.4 Statistical Analysis
3.5 Classification
4 Results and Discussion
4.1 Interpretation of Nonverbal Behavior
4.2 Classification Results
4.3 Limitations
5 Conclusion
References
ExMo: Explainable AI Model Using Inverse Frequency Decision Rules
1 Introduction
2 Related Work
3 Proposed Method
3.1 Review of the Bayesian Rule List (BRL) Algorithm
3.2 Decision Rules from TF-IDF
4 Experimental Results
4.1 Datasets
4.2 Classification Accuracy
4.3 Model Comparison
4.4 Textual Explanation
4.5 Comparison with Model-Agnostic Explanation
4.6 Execution Time
5 Conclusion
References
UX Design and Evaluation of AI-Enabled Systems
A Model of Adaptive Gamification in Collaborative Location-Based Collecting Systems
1 Introduction
2 Related Work
3 Background
3.1 Space-Time Behaviour Definitions
3.2 Game Challenge Definitions
3.3 System Setup Definitions
4 CLCS Automatic Game Challenge Recommendation
4.1 Challenge Repository Population
4.2 Challenge Difficulty Estimation
4.3 Challenge Reward Computation
4.4 Challenge Sorting
5 Discussion
6 Conclusions and Future Work
References
Benchmarking Neural Networks-Based Approaches for Predicting Visual Perception of User Interfaces
1 Introduction
2 Methods and Related Work
2.1 Neural Networks in Computer Vision
2.2 UI Feature Extraction
3 The Experimental Study Description
3.1 Hypotheses and Design
3.2 Material and the Input Data
3.3 Subjects and the Output Data
3.4 The Models: ANN and CNN
4 Results
4.1 Descriptive Statistics
4.2 The Models' Training Time
4.3 Benchmarking the Models' MSEs
4.4 Regression Analysis for MSE
5 Discussion and Conclusion
References
My Tutor is an AI: The Effects of Involvement and Tutor Type on Perceived Quality, Perceived Credibility, and Use Intention
1 Introduction
2 Related Work
2.1 AI Tutors
2.2 The Elaboration Likelihood Model (ELM) and Computers are Social Actors (CASA)
2.3 Attribution Theory
3 Method
3.1 Participants
3.2 Procedure
3.3 Stimuli
3.4 Measurement
4 Results
5 Discussion
5.1 Contributions and Implications
5.2 Limitations
6 Conclusion
References
Design of AI-Enabled Application to Detect Ayurvedic Nutritional Values of Edible Items and Suggest a Diet
1 Introduction
2 Literature Review and Related Works
2.1 Understanding Ayurveda
2.2 Understanding Ayurvedic Diet System
2.3 Understanding Quantified Self
2.4 Understanding Major Determinants of Food Choice
3 Research Approach
4 Interview Study
4.1 Study Setup and Method
4.2 Results of Initial Interview Study
5 Design and Implementation
5.1 Determination of Nutritional Values and Ayurvedic Gunas for Food Items
5.2 Diet Suggestions Based on Body Type
6 Usability Testing
6.1 Task 1: Determine Your Body Type in the Application Using Quiz
6.2 Task 2: Scan Any Food Item and Determine Its Ayurvedic Nutritional Information
6.3 Task 3: Track Your Diet and Mood in the Application
6.4 Gamification
7 Conclusion
References
An AI-Based Decision Support System for Quality Control Applied to the Use Case Donor Cornea
1 Introduction
2 Related Work
3 Decision Support System
3.1 Data
3.2 Graphical Analytic Tools
3.3 Case-Based Reasoning as a Tool for Explainability
3.4 Machine Learning Classifiers
3.5 Aggregation
3.6 Graphical User Interface
4 Evaluation
4.1 Study Set-Up
4.2 Study Execution
4.3 Study Results
5 Summary and Future Work
References
Design and Implementation of Platform Protocol and Client of Hakka Residential System Based on Artificial Intelligence
1 Introduction
2 Method
2.1 Application Fields of Artificial Intelligence
2.2 Hakka Houses
2.3 Smart Home System
2.4 Function of Smart Home System
2.5 Calculation Methods Used in the Experiment
3 Experiment
3.1 Selection of Experimental Research Objects
3.2 Selection of Experimental Measurement Standards
4 Discussion
4.1 Investigation on Design Efficiency of the Two Companies
4.2 Client Utilization Survey Designed by Two Companies
5 Conclusions
References
Framework for User Experience Evaluation in MOOC Platforms
1 Introduction
2 Introduction
2.1 Massive and Open Online Courses
2.2 Classification of MOOC Criteria
2.3 User Experience
2.4 Categories and Factors that Make Up the UX
2.5 UX Dimensions
3 Proposal
3.1 FUXE-MOOC Design
3.2 FUXE-MOOC Components
4 Limitations and Future Research
5 Conclusions
Appendix
References
Evaluation on Comfortable Arousal in Autonomous Driving Using Physiological Indexes
1 Introduction
2 Research Objective
3 Research Method
3.1 Physiological Indexes Based on Feature Importance
3.2 Data Set and Model Creation
4 Experiment
4.1 Participants
4.2 Method
4.3 Experimental Procedure
5 Results and Discussion
6 Conclusions
References
Developing and Testing a New Reinforcement Learning Toolkit with Unreal Engine
1 Introduction
2 Related Works
2.1 Domain-Specific Frameworks
2.2 Environment-Suite Frameworks
2.3 General Frameworks
3 URLT
3.1 Unreal Work Pipeline
3.2 Framework Structure
3.3 Starter Pack
4 User Validation
4.1 Goal and Comparison Tool Choice
4.2 Test Structure and Questionnaire
4.3 Assigned Tasks
4.4 Performed Sessions and Data Processing
4.5 Data Analysis and Considerations
5 Conclusions and Future Work
References
AI Applications in HCI
Evaluation of Webcam-Based Eye Tracking for a Job Interview Training Platform: Preliminary Results
1 Introduction
1.1 Related Work
2 Method
3 Experiment Design
3.1 Participants
3.2 Calibration
3.3 ROI Detection
4 Results
4.1 Calibration Task
4.2 ROI Task
5 Discussion and Conclusion
References
A Systematic Review of Artificial Intelligence and Mental Health in the Context of Social Media
1 Introduction
2 Method
2.1 Data Selection
2.2 Query Selection
2.3 Articles Selection
3 Results
3.1 Sources in Which the Studies Were Published
3.2 Trends in the Number of Studies Overtime
3.3 Social Media Platforms Being Analyzed
3.4 Mental Health Disorders Being Studied
3.5 Machine Learning Models and Features Being Applied
3.6 Summary of Included Studies
4 Discussion
4.1 The Use of Social Media Data is Underutilized for Mental Care
4.2 The Lack of Collaboration Between Seemingly Disconnected Research Communities
4.3 The Lack of Attention to the Human Factors When Conducting the Research
5 Conclusions
References
Object Size Prediction from Hand Movement Using a Single RGB Sensor
1 Introduction
2 Related Work
3 Contribution
4 Methods
4.1 Raw Data Collection
4.2 Data Processing and Movement Kinematics Variables
4.3 Feature Engineering and Classifiers
5 Results
6 Discussion
7 Conclusions
References
Replacing Human Input in Spam Email Detection Using Deep Learning
1 Introduction
2 Email as an Attack Vector
2.1 Spam Detection Approaches
3 Methodology
3.1 Data Sources
3.2 Deep Learning Spam Detection Method (SWEM-max)
4 Results and Discussion
5 Conclusions and Future Work
References
Scene Change Captioning in Real Scenarios
1 Introduction
2 Related Work
2.1 Change Detection
2.2 3D Scene Understanding
2.3 Image Captioning
2.4 Change Captioning Datasets
3 Dataset
3.1 Real Scene Change Captioning Dataset: SCCD_Real
3.2 Simulated Scene Change Captioning Dataset: SCCD_Sim
4 Approach
4.1 Overall Framework
4.2 Scene Encoder
4.3 Caption Generator
5 Experiments
5.1 Experimental Setups
5.2 Experiments on SCCD_Sim
5.3 Experiments on SCCD_Real
6 Conclusions
References
The Impact of Artificial Intelligence on the Investment Decision Process in Venture Capital Firms
1 Introduction
2 Venture Capital
3 The Decision-Making Process
3.1 Decision-Making in Organizations Under Uncertainty
3.2 Human-Related Limitations in Decision-Making
3.3 The Decision-Making Process in Venture Capital
3.4 Process-Related Limitations in VC Firms' Decision-Making
4 Research Methodology
5 Findings
6 Discussion
7 Conclusion
References
A New Human Factor Study in Developing Practical Vision-Based Applications with the Transformer-Based Deep Learning Model
1 Introduction
2 Scope of Study
3 CNN Walk-Through
3.1 Image Classification
3.2 Object Detection
4 Transformer Walk-Through
4.1 Image Classification
4.2 Object Detection
5 Comparative Human Factor Analysis
6 Conclusion
References
Attention-Based CNN Capturing EEG Recording's Average Voltage and Local Change
1 Introduction
2 Related Work
3 Experiment
4 Result
5 Discussion
6 Conclusion
References
Human-AI Collaboration
Customizable Text-to-Image Modeling by Contrastive Learning on Adjustable Word-Visual Pairs
1 Introduction
2 Related Work: Limitation of GAN-Based Generation of Rendering and Further Development
3 Generating Visual Images from Textual Descriptions
3.1 Co-occurrence Modeling of Sequential Words and Visual-Tokens
3.2 Image Synthesis Using Visual Units by GAN Approaching
4 Customize Text-to-Image Models with Contrastive Learning
4.1 Benefits of Applying Contrastive Learning in Text-to-Image Generation Problems
4.2 Contrastive Learning on Increasing Visual Expressions of Images
4.3 Contrastive Learning on Increasing Textual Expressions
4.4 Contrastive Learning for Improving Relevance of Text-Visual Pairs
5 Experimental Results
5.1 Experiments of Suitable Neural-Network Models or Machine Learning
5.2 Experiments of Contrastive-Learning Modeling
References
Trafne: A Training Framework for Non-expert Annotators with Auto Validation and Expert Feedback
1 Introduction
2 Related Work
2.1 Medical Image Annotation
2.2 Efficient Annotation
2.3 Collaborative Crowdsourcing
2.4 Training Non-expert Workers
3 Trafne: Proposed Workflow
3.1 Brain Tumor Image Annotation
3.2 Auto Validation
3.3 Expert Validation
4 Implementation
5 User Study
5.1 Data Preparation
5.2 Participants and Duration
5.3 Conditions
5.4 Procedure
5.5 Measurement
6 Results
6.1 Annotation Quality
6.2 Annotation Results
6.3 Questionnaire
7 Discussion
7.1 Auto Validation Compared with Expert Validation
7.2 Effects of Annotation Feedback
7.3 Potential Applications
8 Limitation and Future Work
9 Conclusion
References
Give Me a Hand: A Scene-Fit Hand Posture Drawing Aid
1 Introduction
2 Related Work
2.1 Leading Causes of Difficulties in Drawing Hand Postures
2.2 Researches and Applications of AI in the Field of Artistic Creation
3 Study1: User Study
3.1 Interview
3.2 Propositional Drawing Task
4 Study2: Prototyping and Validation
4.1 Prototyping
4.2 Validation
5 Discussion and Future Work
5.1 Discussion
5.2 Future Work
6 Conclusion
References
Emotional Communication Between Chatbots and Users: An Empirical Study on Online Customer Service System
1 Introduction
2 Theory and Model
2.1 CASA and Perceived Communication Quality
2.2 Emotional Contagion
3 Hypotheses
3.1 Chatbot Capability Perception
3.2 Warm Perception of Communication Process
3.3 Communication Process Quality Assessment
4 Research Methodology
4.1 Measurement Model
4.2 Structural Model
5 Results and Discussion
5.1 Summary of Results
5.2 Implication for Theory
5.3 Implication for Practice
5.4 Limitations and Future Research
6 Conclusion
References
AI for Speech and Text Analysis
Misinformation in Machine Translation: Error Categories and Levels of Recognition Difficulty
1 Introduction
2 Methodology
3 Results
3.1 Misinformation Categories
3.2 Levels of Difficulty in Misinformation Recognition
4 Discussion
5 Conclusion
References
Transformer-Based Multilingual G2P Converter for E-Learning System
1 Introduction
2 Background
2.1 Grapheme-to-Phoneme
2.2 Machine Translation (MT)
3 Method
3.1 International Phonetic Alphabet
3.2 Transformer
4 Experiment
5 Result and Evaluation
5.1 English-IPA (CET6+GRE) Vs English-IPA (Full)
5.2 French-IPA and Spanish-IPA G2P
6 Conclusion
References
Speech Disorders Classification by CNN in Phonetic E-Learning System
1 Introduction
2 System Design
2.1 APTgt System
2.2 Speech Disorders Classification
3 Method
3.1 Mel-Frequency Cepstral Coefficients
3.2 Dynamic Time Warping
3.3 Convolutional Neural Network
4 Implement and Analysis
4.1 Data Process
4.2 MFCC with DTW Implementation
4.3 CNN Implementation
5 Conclusion and Future Work
References
Say It Right: AI Neural Machine Translation Empowers New Speakers to Revitalize Lemko
1 Introduction
1.1 Problems
1.2 Work so Far
1.3 System Under Study
1.4 Hypothesis
1.5 Predictions
1.6 Methods and Justification
1.7 Principal Results
2 Materials and Methods
2.1 Setup
3 Results
3.1 Results by Machine Translation Service
4 Discussion
References
Extracting and Re-mapping Narrative Text Structure Elements Between Languages Using Self-supervised and Active Few-Shot Learning
1 Introduction
2 Methodologies
2.1 Self-supervised Learning Using Generative Pretrained Transformer-Based Language (GPT-3)
2.2 Active Few-Shot Learning Using GPT-3
2.3 Named Entity Linking Using Wikifier
3 Results and Evaluations
3.1 News Reports Data
3.2 Self-supervised Learning Results Using GPT-3
3.3 Active Few-Shot Learning
3.4 Named Entity Linking
4 Conclusion
References
Predicting Request Success with Objective Features in German Multimodal Speech Assistants
1 Introduction
2 Methods
2.1 Data Set
2.2 Emotion Scores
2.3 Classification of Request Success
3 Results
3.1 Data Preparation
3.2 Relation Between Emotions and Task Success
3.3 Classifier Performance
4 Discussion
4.1 Limitations
5 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken