Knowledge Technology and Systems: Toward Establishing Knowledge Systems Science

Preface
Contents
Chapter 1: Defining Knowledge Technology and Systems
1.1 Knowledge Technology and Challenges
1.1.1 Defining Knowledge Technology
1.1.1.1 A Value Creation Spiral Model
1.1.1.2 Principles of Providing Action Guidelines
1.1.1.2.1 Multimedia Principle
1.1.1.2.2 Intervention Principle
1.1.1.2.3 Emergence Principle
1.1.1.2.4 Evolutionary Falsification Principle
1.1.1.3 Goals of Respective Processes
1.1.1.3.1 Completeness
1.1.1.3.2 Logicality
1.1.1.3.3 Novelty
1.1.1.3.4 Usefulness
1.1.2 Challenges in Developing Knowledge Technology
1.1.2.1 Challenges in Converting Data/Knowledge into Information
1.1.2.1.1 Converting Data into Information
1.1.2.1.2 Converting Knowledge into Information
1.1.2.2 Challenges in Converting Information into Knowledge
1.1.2.2.1 Utilizing Well-Established Rational Analysis Methods
1.1.2.2.2 Utilizing the Cultivated Intuition of People
1.1.2.3 Challenges in Creating Ideas from the Knowledge
1.1.2.3.1 Creating New Ideas Through the Systematization of Knowledge
1.1.2.3.2 Creating New Ideas with Creative Technologies
1.1.2.4 Challenges in Validating the Value of Ideas
1.1.2.4.1 Justifying and Promoting the Ideas
1.1.2.4.2 Implementing the Ideas and Verifying the Value
1.2 Knowledge Systems and Challenges
1.2.1 Defining Knowledge Systems
1.2.1.1 Systems Managing and Creating Knowledge
1.2.1.2 Knowledge Systems Engineering
1.2.1.2.1 Knowledge Gathering and Capture (Corresponding to Observation)
1.2.1.2.2 Knowledge Discovery and Creation (Corresponding to Understanding)
1.2.1.2.3 Knowledge Sharing and Exchange (Corresponding to Emergence)
1.2.1.2.4 Knowledge Integration and Application (Corresponding to Implementation)
1.2.2 Challenges in Developing Knowledge Systems
1.2.2.1 Meta-Synthesis Systems Approach
1.2.2.1.1 Expert Meeting
1.2.2.1.2 Analysis
1.2.2.1.3 Synthesis
1.2.2.1.4 Evaluation Meeting
1.2.2.2 Critical Systems Thinking and Practice
1.2.2.3 Developing a Methodology for Building Knowledge Systems
1.2.2.3.1 (P1) Planning
1.2.2.3.2 (M1) Observation
1.2.2.3.3 (P2) Analysis
1.2.2.3.4 (M2) Understanding
1.2.2.3.5 (P3) Ideation
1.2.2.3.6 (M3) Emergence
1.2.2.3.7 (P4) Synthesis
1.2.2.3.8 (M4) Implementation
1.2.2.3.9 (P5) Evaluation
References
Chapter 2: Big Data Analytics in Healthcare
2.1 Big Data-Driven Paradigm
2.1.1 The Research Background of Big Data Analytics in Healthcare
2.1.2 The Research Framework of Big Data Analytics in Healthcare
2.1.3 Analysis of Clinical Diagnosis and Treatment Process
2.1.4 The Literature Summary of Diagnosis-Treatment Pattern Mining
2.1.4.1 The Related Work of Unifying Diagnosis (UD)
2.1.4.2 The Related Work of Clinical Pathway (CP)
2.1.4.3 The Related Work of Rational Drug Use
2.2 Challenges for Typical Diagnosis-Treatment Pattern Mining
2.2.1 Measuring Similarity Among Diagnosis and Treatment Records
2.2.1.1 Similarity Measure of Patients´ Diagnostic Records
2.2.1.2 Similarity Measure of Patients´ Treatment Records
2.2.2 Extracting Typical Diagnosis-Treatment Patterns from EMRs
2.2.2.1 Typical Diagnosis Pattern Extraction from Clustering Results
2.2.2.2 Typical Treatment Pattern Extraction from Clustering Results
2.2.3 Predicting Typical Diagnosis Patterns
2.2.4 Evaluating and Recommending Typical Treatment Patterns
2.3 Typical Diagnosis Pattern Mining for Clinical Research
2.4 Typical Treatment Pattern Mining for Clinical Research
2.4.1 Typical Treatment Regimen Mining from Doctor Order Content View
2.4.2 Typical Drug Use Pattern Mining from Doctor Order Duration View
2.4.3 Typical Treatment Process Mining from Doctor Order Sequence View
2.4.4 Typical Treatment Pattern Mining from Multi-View Similarity Network Fusion
2.4.5 The Examination of Typical Treatment Pattern Mining Approaches, Limitations, and Open Issues
2.5 Conclusions
References
Chapter 3: Knowledge Discovery from Online Reviews
3.1 Overview of Online Reviews Mining
3.1.1 Product Ranking System Based on Online Reviews
3.1.2 User Preference Analysis
3.1.3 Review Usefulness Analysis
3.1.4 Product Competitive Analysis
3.2 Online Reviews Information Mining Techniques
3.2.1 Information Extraction Technique
3.2.1.1 Named Entity Recognition
3.2.1.2 Relationship Extraction
3.2.1.3 Event Extraction
3.2.2 Sentiment Analysis Technique
3.2.2.1 Sentiment Dictionaries
3.2.2.2 Machine Learning
3.2.2.3 Deep Learning
3.2.3 Text Categorization Technique
3.2.3.1 Traditional Methods
3.2.3.2 Fuzzy Logic-Based Methods
3.2.3.3 Deep Learning-Based Methods
3.3 Commercial Value Discovery of Online Reviews
3.3.1 Word-of-Mouth Ranking of Products by Using Online Reviews
3.3.2 Mining Relationships Between Retail Prices and Online Reviews
3.3.2.1 Model Building
3.3.2.2 Model Searching by Using GP
3.3.2.3 Model Selection
3.3.3 Personalized Online Reviews Ranking Based on User Preference
3.3.3.1 Concept Defining
3.3.3.2 Problem Modeling
3.3.3.3 Algorithm
3.4 Expected Future of Techniques for Online Reviews
3.4.1 Deep Migration Learning
3.4.2 Multimodal Data Processing
3.4.3 Text Categorization Tasks
References
Chapter 4: Machine Learning for Solving Unstructured Problems
4.1 Online Deceptive Review Identification Based on Generative Adversarial Network
4.1.1 Introduction
4.1.2 Generative Adversarial Network
4.1.3 Feature Extraction from Textual Reviews
4.1.4 Online Deceptive Review Identification
4.1.5 The Proposed Method GAN-RDE
4.1.6 The Dataset
4.1.6.1 Preprocessing of Review Data
4.1.6.2 Feature Extraction
4.1.7 Experiment Setup
4.1.8 Experiential Results
4.1.9 Concluding Remarks
4.2 Fine-Grained Bug Localization Based on Word Vectors
4.2.1 Introduction
4.2.2 Problem Description
4.2.3 The Proposed MethodLocator Approach
4.2.4 Method Body Vector Representation and Expansion
4.2.5 Bug Report and Method Body Similarity Calculation and Ranking
4.2.6 Experiments
4.2.6.1 Building the Benchmark Dataset
4.2.6.2 Experimental Setup
4.2.6.3 The Baselines
4.2.6.4 Evaluation Metrics
4.2.7 Experiment Results and Analysis
4.2.8 Concluding Remarks
References
Chapter 5: Qualitative Modeling to Extract Knowledge for Problem Structuring
5.1 Introduction
5.2 Qualitative Meta-Synthesis for Problem Structuring
5.2.1 Courtney´s DSS Framework for Wicked Problem-Solving
5.2.2 A Working Process of MSA
5.3 Supporting Technologies for Qualitative Meta-Synthesis
5.3.1 Basic Ideas of CorMap and iView Technologies
5.3.2 Features of CorMap and iView for Qualitative Meta-Synthesis
5.3.3 Applications to Mining of Community Opinions
5.3.3.1 Societal Risk Perception by Community Opinions Collected by Survey
5.3.3.2 Mining Community Opinions from the Online Media by CorMap
5.3.3.3 Perceiving Online Community Concerns by iView Analysis
5.4 Generating Storyline for the Big Picture of the Public Concerns
5.4.1 Generating Storyline as Multi-View Graph by Dominating Set
5.4.1.1 The Framework of Generating Storyline Using Dominating Set
5.4.1.2 Consistency Graph Construction
5.4.1.3 Minimum-Weight Dominating Set (MWDS)
5.4.1.4 The Directed Maximum Spanning Tree
5.4.1.5 One Experiment toward the Evolution of the Public Concerns from BBS
5.4.2 Generating Storyline Using Risk Map
5.4.2.1 Concepts of Risk Map
5.4.2.1.1 Coherence
5.4.2.1.2 Coverage
5.4.2.1.3 Connectivity
5.4.2.2 Risk Map Generation
5.4.2.3 One Experiment Toward the Public Concerns from Baidu Hot News Search Words
5.5 Summary
References
Chapter 6: Agent-Based Simulation of Low Carbon Emissions Product Diffusion
6.1 Introduction
6.2 Literature Review
6.2.1 Modeling Innovation and the Diffusion of Low Emissions Products
6.2.2 ABMs and Social Influence
6.3 The Agent-Based Model
6.3.1 Agents and Elements in the Model
6.3.2 Consumer Agents
6.3.2.1 Peer Effect among Consumers
6.3.2.2 Consumers´ Decision to Buy Products
6.3.3 Producer Agents
6.3.3.1 Producers´ Entries and Exits
6.3.3.2 Technological Learning Effect with Cumulative Adoption
6.3.3.3 Price Mark, R&D Budget, and New Products
6.3.4 Policies for Promoting the Diffusion of Low Emissions Products
6.4 Simulations and Analyses
6.4.1 Initializing the Baseline Simulations
6.4.2 How Different Fifth Attribute Timing Influences the Diffusion of Low Emissions Products
6.4.3 How Different Peer Effect and Network Structure Influence the Diffusion of Low Emissions Products
6.4.4 How Policies Affect the Diffusion of Low Emissions Products
6.5 Concluding Remarks
Appendix: Mathematical Formulations of the Agent-Based Model
Producer Agents and their Products
Initial Producers and Products
Selling Products and Making Profit
R&D and Discovering New Products
Exit and Entry of Producers
Consumer Agents
Social Influence among Consumer Agents
Consumers´ Decision to Buy a Product
Educating Consumers to Be more Environmental-Friendly
References
Chapter 7: Emotional Product Development: Concepts, Framework, and Methodologies
7.1 Introduction
7.1.1 New Product Development
7.1.2 Emotional New Product Development
7.1.3 The Concept of Product
7.1.4 Motivations and Outline
7.2 Emotion and Kansei: Conceptualization and Measurement
7.2.1 Conceptualization of Emotion
7.2.2 Measurement of Emotion
7.2.3 Conceptualization and Measurement of Emotion as Kansei
7.3 Emotional Product Development and Kansei Engineering
7.3.1 The Emotion-Driven Innovation Process
7.3.1.1 Emotional Knowledge Acquisition
7.3.1.2 Emotional Goal Definition
7.3.1.3 Emotional Idea Generation
7.3.1.4 Summary
7.3.2 Kansei Engineering as a Powerful Methodology for Emotional Product Development
7.3.2.1 Choice of the Domain
7.3.2.2 Spanning Attributes
7.3.2.3 Kansei Experiment
7.3.2.4 Relationship Modeling
7.3.2.5 Summary
7.4 A Physical-Emotion-Satisfaction Framework for Emotional Product Development
7.4.1 The Physical-Emotion Link
7.4.2 The Emotion-Satisfaction Link
7.4.3 The Proposed Framework
7.5 Detailed Descriptions of the Physical-Emotion-Satisfaction Framework
7.5.1 Emotional Knowledge Acquisition
7.5.1.1 Offline Acquisition
7.5.1.2 Online Acquisition
7.5.2 Emotional Goal Definition
7.5.2.1 Emotional Need Analysis
7.5.2.1.1 Brief Introduction to Kano Model
7.5.2.1.2 Offline Emotional Need Analysis
7.5.2.1.3 Online Emotional Need Analysis
7.5.2.2 Physical Need Analysis
7.5.2.2.1 Brief Introduction to QFD Model
7.5.2.2.2 Physical Need Analysis Based on QFD Model
7.5.3 Emotional Idea Generation
7.5.3.1 Modeling the Relationships Between Emotional and Physical Attributes
7.5.3.2 Modeling the Relationships Between Emotional Attributes and Satisfaction
7.5.3.2.1 Decision Analysis Approaches
Individual Emotional Satisfaction
Multi-Attribute Emotional Satisfaction
7.5.3.2.2 Statistical Approaches
7.6 Conclusions and Future Work
7.6.1 Summary
7.6.2 Future Research Directions
References
Chapter 8: Knowledge Synthesis and Promotion
8.1 Knowledge Construction Systems Methodology
8.1.1 Knowledge Construction System Model
8.1.2 Knowledge Construction Diagram
8.1.3 Constructive Evolutionary Objectivism
8.1.4 Example 1: Thinking About the Summer Menu of a Sushi Restaurant
8.1.5 Example 2: Building a Healthy and Lively Community
8.2 Knowledge Synthesis Enablers
8.2.1 Defining Enablers for Knowledge Synthesis
8.2.2 Structural Equation Modeling
8.2.3 Covariance Structure Analysis
8.2.3.1 Confirmatory Factor Analysis
8.2.3.2 Regression Analysis
8.2.3.3 Multivariate Regression Analysis
8.3 Knowledge Promotion Stories
8.3.1 Content Marketing and Storytelling
8.3.2 Steps to Create a Promotion Story
8.3.2.1 Stage 1: Considering a Strategy for Story Creation at Intervention
8.3.2.2 Stage 2: Developing Basic Stories at Intelligence, Involvement, and Imagination
8.3.2.3 Stage 3: Creating Promotion Stories at Integration
8.3.3 A Story Creation Project
References
Chapter 9: Group Decision-Making
9.1 Introduction
9.2 GDM Based on Information Fusion
9.2.1 Aggregation for Rankings
9.2.2 Aggregation for Evaluations
9.2.3 Aggregation for Pairwise Comparison
9.3 GDM Based on Consensus Improving
9.3.1 Process-Oriented Consensus Improving
9.3.2 Content-Oriented Consensus Improving
9.3.3 GDM Based on Social Network
9.4 GDM Based on Behavior
9.4.1 GDM Considering Behavior
9.4.2 Behaviors in GDM
9.5 Application of GDM
9.6 Expected Future of GDM
9.6.1 The GDM in Blockchain
9.6.2 The GDM Using Machine Learning
9.6.3 The Use and the Expression of GDM Behavior
References
Index