Doing Computational Social Science A Practical Introduction

Discover Your Online Resources!
Acknowledgements
About the Author
Introduction: Learning to Do Computational Social Science
	0.1 Who Is This Book For?
	0.2 Roadmap
	0.3 Datasets Used in This Book
	0.4 Learning Materials
	0.5 Conclusion
Part I Foundations
	1 Setting Up Your Open Source Scientific Computing Environment
		1.1 Learning Objectives
		1.2 Introduction
		1.3 Command Line Computing
		1.4 Open Source Software
		1.5 Version Control Tools
		1.6 Virtualization Tools
		1.7 Putting the Pieces Together: Python, Jupyter, conda, and git
		1.8 Conclusion
	2 Python Programming: The Basics
		2.1 Learning Objectives
		2.2 Learning Materials
		2.3 Introduction
		2.4 Learning Python
		2.5 Python Foundations
		2.6 Conclusion
	3 Python Programming: Data Structures, Functions, and Files
		3.1 Learning Objectives
		3.2 Learning Materials
		3.3 Introduction
		3.4 Working With Python’s Data Structures
		3.5 Custom Functions
		3.6 Reading and Writing Files
		3.7 Pace Yourself
		3.8 Conclusion
	4 Collecting Data From Application Programming Interfaces
		4.1 Learning Objectives
		4.2 Learning Materials
		4.3 Introduction
		4.4 What Is an API?
		4.5 Getting Practical: Working With APIs
		4.6 Conclusion
	5 Collecting Data From the Web: Scraping
		5.1 Learning Objectives
		5.2 Learning Materials
		5.3 Introduction
		5.4 An HTML and CSS Primer for Web Scrapers
		5.5 Developing Your First Web Scraper
		5.6 Ethical and Legal Issues in Web Scraping
		5.7 Conclusion
	6 Processing Structured Data
		6.1 Learning Objectives
		6.2 Learning Materials
		6.3 Introduction
		6.4 Practical Pandas: First Steps
		6.5 Understanding Pandas Data Structures
		6.6 Aggregation and Grouped Operations
		6.7 Working With Time-Series Data
		6.8 Combining Dataframes
		6.9 Conclusion
	7 Visualization and Exploratory Data Analysis
		7.1 Learning Objectives
		7.2 Learning Materials
		7.3 Introduction
		7.4 Iterative Research Workflows: EDA and Box’s Loop
		7.5 Effective Visualization
		7.6 Univariate EDA: Describing and Visualizing Distributions
		7.7 Multivariate EDA
		7.8 Conclusion
	8 Latent Factors and Components
		8.1 Learning Objectives
		8.2 Learning Materials
		8.3 Introduction
		8.4 Latent Variables and the Curse of Dimensionality
		8.5 Conducting a Principal Component Analysis in Sklearn
		8.6 Conclusion
Part II Fundamentals of Text Analysis
	9 Processing Natural Language Data
		9.1 Learning Objectives
		9.2 Learning Materials
		9.3 Introduction
		9.4 Text Processing
		9.5 Normalizing Text via Lemmatization
		9.6 Part-of-Speech Tagging
		9.7 Syntactic Dependency Parsing
		9.8 Conclusion
	10 Iterative Text Analysis
		10.1 Learning Objectives
		10.2 Learning Materials
		10.3 Introduction
		10.4 Exploration in Context: Text Analysis Pipelines
		10.5 Count-Based Feature Extraction: From Strings to a Bag of Words
		10.6 Close Reading
		10.7 Conclusion
	11 Exploratory Text Analysis – Working With Word Frequencies and Proportions
		11.1 Learning Objectives
		11.2 Learning Materials
		11.3 Introduction
		11.4 Scaling Up: Processing Political Speeches
		11.5 Creating DTMs With Sklearn
		11.6 Conclusion
	12 Exploratory Text Analysis – Word Weights, Text Similarity, and Latent Semantic Analysis
		12.1 Learning Objectives
		12.2 Learning Materials
		12.3 Introduction
		12.4 Exploring Latent Semantic Space With Matrix Decomposition
		12.5 Conclusion
Part III Fundamentals of Network Analysis
	13 Social Networks and Relational Thinking
		13.1 Learning Objectives
		13.2 Learning Materials
		13.3 Introduction
		13.4 What Are Social Networks?
		13.5 Working With Relational Data
		13.6 Walk Structure and Network Flow
		13.7 Conclusion
	14 Connection and Clustering in Social Networks
		14.1 Learning Objectives
		14.2 Learning Materials
		14.3 Introduction
		14.4 Micro-Level Network Structure and Processes
		14.5 Detecting Cohesive Subgroups and Assortative Structure
		14.6 Conclusion
	15 Influence, Inequality, and Power in Social Networks
		15.1 Learning Objectives
		15.2 Learning Materials
		15.3 Introduction
		15.4 Centrality Measures: The Big Picture
		15.5 Shortest Paths and Network Flow
		15.6 Betweenness Centrality, Two Ways
		15.7 Popularity, Power, and Influence
		15.8 Conclusion
		15.9 Chapter Appendix
	16 Going Viral: Modelling the Epidemic Spread of Simple Contagions
		16.1 Learning Objectives
		16.2 Learning Materials
		16.3 Introduction
		16.4 Epidemic Spread and Diffusion
		16.5 Modelling Spreading Processes With NDlib
		16.6 Simple Contagions and Epidemic Spread
		16.7 Conclusion
	17 Not So Fast: Modelling the Diffusion of Complex Contagions
		17.1 Learning Objectives
		17.2 Learning Materials
		17.3 Introduction
		17.4 From Simple to Complex Contagions
		17.5 Beyond Local Neighbourhoods: Network Effects and Thresholds
		17.6 Threshold Models for Complex Contagions
		17.7 Conclusion
Part IV Research Ethics and Machine Learning
	18 Research Ethics, Politics, and Practices
		18.1 Learning Objectives
		18.2 Learning Materials
		18.3 Introduction
		18.4 Research Ethics and Social Network Analysis
		18.5 Informed Consent, Privacy, and Transparency
		18.6 Bias and Algorithmic Decision-Making
		18.7 Ditching the Value-Free Ideal for Ethics, Politics, and Science
		18.8 Conclusion
	19 Machine Learning: Symbolic and Connectionist
		19.1 Learning Objectives
		19.2 Learning Materials
		19.3 Introduction
		19.4 Types of Machine Learning
		19.5 Symbolic and Connectionist Machine Learning
		19.6 Conclusion
	20 Supervised Learning With Regression and Cross-validation
		20.1 Learning Objectives
		20.2 Learning Materials
		20.3 Introduction
		20.4 Supervised Learning With Linear Regression
		20.5 Classification With Logistic Regression
		20.6 Conclusion
	21 Supervised Learning With Tree-Based Models
		21.1 Learning Objectives
		21.2 Learning Materials
		21.3 Introduction
		21.4 Rules-Based Learning With Trees
		21.5 Ensemble Learning
		21.6 Evaluation Beyond Accuracy
		21.7 Conclusion
	22 Neural Networks and Deep Learning
		22.1 Learning Objectives
		22.2 Learning Materials
		22.3 Introduction
		22.4 The Perceptron
		22.5 Multilayer Perceptrons
		22.6 Training ANNs With Backpropagation and Gradient Descent
		22.7 More Complex ANN Architectures
		22.8 Conclusion
	23 Developing Neural Network Models With Keras and TensorFlow
		23.1 Learning Objectives
		23.2 Learning Materials
		23.3 Introduction
		23.4 Getting Started With Keras
		23.5 End-to-End Neural Network Modelling
		23.6 Conclusion
Part V Bayesian Data Analysis and Generative Modelling with Probabilistic Programming
	24 Statistical Machine Learning and Generative Models
		24.1 Learning Objectives
		24.2 Learning Materials
		24.3 Introduction
		24.4 Statistics, Machine Learning, and Statistical Machine Learning: Where Are the Boundaries and What Do They Bind?
		24.5 Generative Versus Discriminative Models
		24.6 Conclusion
	25 Probability: A Primer
		25.1 Learning Objectives
		25.2 Learning Materials
		25.3 Introduction
		25.4 Foundational Concepts in Probability Theory
		25.5 Probability Distributions and Likelihood Functions
		25.6 Continuous Distributions, Probability Density Functions
		25.7 Joint and Conditional Probabilities
		25.8 Bayesian Inference
		25.9 Posterior Probability
		25.10 Conclusion
	26 Approximate Posterior Inference With Stochastic Sampling and MCMC
		26.1 Learning Objectives
		26.2 Learning Materials
		26.3 Introduction
		26.4 Bayesian Regression
		26.5 Stochastic Sampling Methods
		26.6 Conclusion
Part VI Probabilistic Programming and Bayesian Latent Variable Models for Structured, Relational, and Text Data
	27 Bayesian Regression Models With Probabilistic Programming
		27.1 Learning Objectives
		27.2 Learning Materials
		27.3 Introduction
		27.4 Developing Our Bayesian Model
		27.5 Conclusion
	28 Bayesian Hierarchical Regression Modelling
		28.1 Learning Objectives
		28.2 Learning Materials
		28.3 Introduction
		28.4 So, What’s a Hierarchical Model?
		28.5 Goldilocks and the Three Pools
		28.6 The Best Model Our Data Can Buy
		28.7 The Fault in Our (Lack of) Stars
		28.8 Conclusion
	29 Variational Bayes and the Craft of Generative Topic Modelling
		29.1 Learning Objectives
		29.2 Learning Materials
		29.3 Introduction
		29.4 Generative Topic Models
		29.5 Topic Modelling With Gensim
		29.6 Conclusion
	30 Generative Network Analysis With Bayesian Stochastic Block Models
		30.1 Learning Objectives
		30.2 Learning Materials
		30.3 Introduction
		30.4 Block Modelling With Graph-Tool
		30.5 Conclusion
Part VII Embeddings, Transformer Models, and Named Entity Recognition
	31 Can We Model Meaning? Contextual Representation and Neural Word Embeddings
		31.1 Learning Objectives
		31.2 Learning Materials
		31.3 Introduction
		31.4 What Words Mean
		31.5 What Are Neural Word Embeddings?
		31.6 Cultural Cartography: Getting a Feel for Vector Space
		31.7 Learning Embeddings With Gensim
		31.8 Comparing Embeddings
		31.9 Conclusion
	32 Named Entity Recognition, Transfer Learning, and Transformer Models
		32.1 Learning Objectives
		32.2 Learning Materials
		32.3 Introduction
		32.4 Named Entity Recognition
		32.5 Transformer Models
		32.6 Conclusion
References
Index