Social Computing with Artificial Intelligence

Preface
Contents
1 Introduction
	1.1 Research Background
	1.2 Mainstreams of Research Field
		1.2.1 Social Data Perception and Knowledge Discovery
		1.2.2 Community Modeling of Individuals and Groups
		1.2.3 Information Dissemination and Dynamic Evolution of Network
		1.2.4 Decision Support and Application
	1.3 Structure of This Book
	References
Part IData
2 Data Collection
	2.1 Data Types and Sources
	2.2 Data Collection and Tools
		2.2.1 Data Acquisition
		2.2.2 Common Data Processing Toolkit
3 Data Processing Methodology
	3.1 Data Processing Principles
		3.1.1 Behavior Tracking
	3.2 Data Processing Methods
Part IIAI Models and Algorithms
4 Supervised and Unsupervised Learning Models
	4.1 Supervised Learning Models
		4.1.1 Generalized Linear Algorithms
		4.1.2 Decision Trees
		4.1.3 Nearest Neighbors
		4.1.4 Bayesian Methods
		4.1.5 Bayesian Regression
		4.1.6 Gaussian Processes
		4.1.7 Support Vector Machines
		4.1.8 Ensemble Methods
	4.2 Unsupervised/Semi-supervised Learning Models
		4.2.1 Dimensionality Reduction Algorithms
		4.2.2 Clustering Algorithms
	References
5 State-of-the-Art Artificial Intelligence Algorithms
	5.1 Deep Learning
		5.1.1 Deep Neural Network
		5.1.2 Convolutional Neural Network
		5.1.3 Recurrent Neural Network and Long Short-Term Network
	5.2 Reinforcement Learning
		5.2.1 Reinforcement Learning Algorithm
		5.2.2 Deep Reinforcement Learning
	5.3 Brother Learning
	5.4 Epiphany Learning
		5.4.1 The Concept of Epiphany
		5.4.2 Learning with Teachers, Learning without Teachers, and Epiphany Learning
		5.4.3 Structured Description of Epiphany Learning
	References
6 Social Network Data Mining and Knowledge Discovery
	6.1 Online Social Networks Text Processing Models
		6.1.1 Information Extraction
		6.1.2 Keywords Mining
		6.1.3 Topic Detection and Tracking
		6.1.4 Automatic Summarization
		6.1.5 Sentiment Analysis
	6.2 Online Social Networks Image Recognition Models
		6.2.1 Image Retrieval
		6.2.2 Image Object Detection and Classification
	References
7 Social Networks Structure Analysis and Online Community Discovery
	7.1 Online Social Networks Topology Structure and Models
		7.1.1 Basic Concepts of Network Topology Structure
		7.1.2 Regular Networks and Random Graphs
		7.1.3 Small World Network Model
		7.1.4 Scale-Free Network Model
		7.1.5 Local World Evolutionary Network Model
	7.2 Online Social Networks Community Discovery Models
		7.2.1 Basic Concepts of Community
		7.2.2 Online Networks Community Discovery-Related Technologies Model
		7.2.3 Evaluation Indicators of Community Discovery Model
	References
8 Social Network Propagation Mechanism and Online User Behavior Analysis
	8.1 Network Propagation Mechanism and Dynamic Analysis
		8.1.1 Propagation Critical Value Theory for Complex Networks
		8.1.2 Propagation Dynamics of Complex Networks
	8.2 Online Crowd Behavior and Influence Model
		8.2.1 Measurement of User Node Impact Based on Topological Structure
		8.2.2 Impact Measurement Based on Content and Behavior Characteristics
	8.3 Online Social Networks User Role Identification
		8.3.1 Uncertain Role Recognition Method
		8.3.2 Role Recognition
	References
Part IIIApplications
9 Social Computing Application in Public Security and Emergency Management
	9.1 Introduction
	9.2 Problem Description and Extraction
		9.2.1 Qualitative Analysis of Car Hijacking Scenario
		9.2.2 Quantitative Description of Information Value of Social Networks
	9.3 Social Computing in Emergency Problem
		9.3.1 Emergency Decision Support Architecture for Bus Hijacking
		9.3.2 Anomaly Detection Algorithm Model Based on SIFT Features and SVM Classification
	References
10 Social Computing Application in Business Decision Support
	10.1 Introduction
	10.2 Social Computing in Business Decision Support
		10.2.1 Model Overall Framework Diagram
		10.2.2 News Type Division Model
		10.2.3 Event Research Model
	References
11 Social Computing Application in Unsupervised Oracle Handwriting Recognition Based on Pic2Vec Image Content Mapping
	11.1 Image Feature Extraction Method
	11.2 Experiments and Analysis
	11.3 Thinking over Oracle Bone Inscriptions
12 Social Computing Application in Online Crowd Behavior and Psychology
	12.1 Introduction
		12.1.1 Online Social Network Rumors and Traditional Rumors
		12.1.2 Key Issues in OSN Rumor Detection
		12.1.3 OSN Rumor Detection Open Data Resources
	12.2 Content Classification Based on Machine Learning Rumor Detection
	12.3 Network Structure Based Rumor Source Detection
	References
Appendix Mathematical Basis
A.1 Basis of Vectors and Matrices
A.1 1. Vector Basis
A.1 2. Matrix Basis
A.2 Derivatives and Partial Derivatives
A.2 1. Derivatives in Neural Networks
A.2 2. Partial Derivatives in Neural Networks
A.3 Gradient Descent Method
A.3.1 Derivation Process of One-Dimensional Gradient Descent Method
A.3 2. Gradient Descent Formula of Binary Function
Index