Mapping Texts: Computational Text Analysis for the Social Sciences

✍ Scribed by Dustin S. Stoltz, Marshall A. Taylor

• Publisher: Oxford University Press
• Year: 2024
• Tongue: English
• Leaves: 320
• Series: Computational Social Science
• Category: Library

✦ Synopsis

Learn how to conduct a robust text analysis project from start to finish--and then do it again.

Mining is the dominant metaphor in computational text analysis. When mining texts, the implied assumption is that analysts can find kernels of truth--they just have to sift through the rubbish first. In this book, Dustin Stoltz and Marshall Taylor encourage text analysts to work with a different metaphor in mind: mapping. When mapping texts, the goal is not necessarily to find meaningful needles in the haystack, but instead to create reductions of the text to document patterns. Just like with cartographic maps, though, the type and nature of the textual map is dependent on a range of decisions on the part of the researcher. Creating reproducible workflows is therefore critical for the text analyst.

Mapping Texts offers a practical introduction to computational text analysis with step-by-step guides on how to conduct actual text analysis workflows in the R statistical computing environment. The focus is on social science questions and applications, with data ranging from fake news and presidential campaigns to Star Trek and pop stars. The book walks the reader through all facets of a text analysis workflow--from understanding the theories of language embedded in text analysis, all the way to more advanced and cutting-edge techniques.

The book will prove useful not only to social scientists, but anyone interested in conducting text analysis projects.

✦ Table of Contents

Preface
I Bounding Texts
Text in Context
What Is Language?
What Is Text?
Corpus Building
Texts Are Not People
Balance, Range, and Representativeness
II Prerequisites
Computing Basics
Brass Tacks
Math Basics
The Fundamentals
Comparing Vectors
III Foundations
Acquiring Text
Public Text Datasets
Optical Character Recognition
From Text to Numbers
Units of Analysis
IV Below the Document
Wrangling Words
Character Encoding
Markup Characters
Tagging Words
Dictionary Tagging
Named-Entity Recognition
V The Document and Beyond
Core Deductive
Discrete Indicators
Weighted Indicators
Core Inductive
Document Similarity
Extended Inductive
Inference and Topic Models
Extended Deductive
Supervision and Validation
Project Workflow and Iteration
The Paradox of the Complete Map
Containerize Our Projects
Corpus Building
Redrawing Boundaries
Math Basics
Our Dear Friend, the Matrix
II Prerequisites
Computing Basics
Data Visualization
Where to from Here
From Text to Numbers
Weighting and Norming
Extended Inductive
Word Embeddings: The Next Generation
Extended Deductive
Deductive Analysis with Pretrained Models
Math Basics
Comparing Distributions
A Little Math Goes a Long Way
III Foundations
Acquiring Text
Legal and Ethical Side of Scraping
From Text to Numbers
Token Distributions
Core Inductive
Topic Modeling
Extended Deductive
Training with Neural Networks
III Foundations
Acquiring Text
Automated Audio Transcription
Application Programming Interfaces (to.APIs)to.
Automated Web Scraping
From Text to Numbers
Document Features
IV Below the Document
Wrangling Words
Removing and Replacing Characters
Replacing Words
Core Inductive
Document Clustering
Extended Deductive
Classic Training with Supervision
Project Workflow and Iteration
Memoing and Datasheets
Repeating, Replicating, and Simulating the Null
From Text to Numbers
Term Features
Dimension Reduction
Extended Inductive
Inductive Analysis with Word Embeddings
IV Below the Document
Wrangling Words
Removing Words and Stoplists
Wrangling Workflow
Tagging Words
Part-of-Speech and Dependency Parsing
V The Document and Beyond
Core Deductive
Selecting and Building Dictionaries
Extended Inductive
Word Embeddings: The First Generation
Project Workflow and Iteration
Knowledge Takes a Village
Tagging Words
V The Document and Beyond
Core Deductive
Core Inductive
Extended Inductive
Extended Deductive
Inference with Text Networks
Project Workflow and Iteration