Computational Analysis of Communication

This book is aimed at students and (aspiring) practitioners of computational social science, especially related to the analysis of digital communication. With this book and the accompanying code examples and video tutorials, you can learn data wrangling, machine learning, text analysis, and more. All examples are given side-by-side in Python and R, allowing you to pick your fav...

(展开全部)

This book is aimed at students and (aspiring) practitioners of computational social science, especially related to the analysis of digital communication. With this book and the accompanying code examples and video tutorials, you can learn data wrangling, machine learning, text analysis, and more. All examples are given side-by-side in Python and R, allowing you to pick your favorite language but also showing the differences and many similarities at a glance.

Dr. Wouter van Atteveldt is an Associate Professor of Political Communication at Vrije University, Amsterdam. He is Chair of Computational Methods of the International Communication Association, and Founding Chief Editor of Computational Communication Science. He has published extensively on innovative methods for analyzing political text and contributed to a number of relevant...

(展开全部)

Dr. Wouter van Atteveldt is an Associate Professor of Political Communication at Vrije University, Amsterdam. He is Chair of Computational Methods of the International Communication Association, and Founding Chief Editor of Computational Communication Science. He has published extensively on innovative methods for analyzing political text and contributed to a number of relevant R and Python packages.

Dr. Damian Trilling is an Assistant Professor, Department of Communication Science, at the University of Amsterdam, and Associate Editor of Computational Communication Research. His research uses computational methods such as the analysis of digital trace data and large-scale text analysis to study the use and effects of news media. He has developed extensive teaching materials to introduce social scientists to the Python programming language.

Dr. Carlos Arcila Calderón is an Assistant Professor, Department of Sociology and Communication, at the University of Salamanca, Chief Editor of the journal Disertaciones, and member of the Editorial Board of Computational Communication Research. He has published extensively on new media and social media studies, and has led the prototype Autocop, a Spark-based environment to run distributed supervised sentiment analysis of Twitter messages.

Table of Contents
Part 1: Getting started
Chapter 1: Introduction
The role of computational analysis in social science
Why Python and/or R?
How to use this book?
· · · · · · (更多)

Table of Contents
Part 1: Getting started
Chapter 1: Introduction
The role of computational analysis in social science
Why Python and/or R?
How to use this book?
Installing R and Python
Installing third-party packages
Chapter 2: Fun with data and visualizations
Fun with tweets
Fun with textual data
Fun with visualizing geographic information
Fun with networks
Chapter 3: Programming concepts for data analysis
About objects and data types
Simple control structures: loops and conditions
Functions and methods
Chapter 4: How to write code
Re-using code: how not to re-invent the wheel
Understanding errors and getting help
Best practices: beautiful code, GitHub, and notebooks
Part 2: Cleaning and analyzing data
Chapter 5: From file to data frame and back
Why and when do we use data frames?
Reading and saving data
Data from online sources
Chapter 6: Data wrangling
Filtering, selecting, and calculating
Calculating values
Grouping and aggregating
Merging data
Reshaping data: wide to long and long to wide
Restructuring ‘messy’ data
Chapter 7: Exploratory data analysis
Simple exploratory statistics
Visualizing data
Clustering and dimensionality reduction
Chapter 8: Statistical Modeling and Supervised Machine Learning
Statistical modeling and prediction
Concepts and Principles
Classical Machine Learning: From Naive Bayes to neural networks
Deep Learning
Validation and best practices
Part 3: Text Analysis
Chapter 9: Processing text
Text as a string of characters
Regular expressions
Using Regular expressions in Python and R
Chapter 10: Text as data
The bag of words and term-document matrix
Cleaning, weighting, selecting features
Advanced representations f text
Natural language processing
Chapter 11: Automatic analysis of text
Overview of text analysis methods
Dictionary approaches to text analysis
Supervised text analysis: automatic classification and sentiment analysis
Unsupervised text analysis: topic modeling
Part 4: Beyond Structured Data
Chapter 12: Scraping online data
Using open web APIs
Retrieving and parsing web pages
Authentication, cookies, and sessions
Ethical, legal and practical considerations
Chapter 13: Introduction to Network Data
Representing and visualizing networks
Social Network Analysis
Chapter 14: Introduction to Image and Video Data
Beyond text analysis: Images, audio, and video
Using existing APIs for analysing image data
Storing, representing, and converting image and video data
Deep learning for image analysis
Part 5: Next Steps
Chapter 15: Scaling up and distributing
Storing data in SQL and noSQL databases
Using cloud computing
Publishing your source
Distributing your software as container
Chapter 16: Where to go next?
How far have we come?
Where to go next?
Open, transparent, and Ethical Computational Science
· · · · · · (收起)