You are here

Text Mining
Share

Text Mining
A Guidebook for the Social Sciences



April 2016 | 208 pages | SAGE Publications, Inc
Online communities generate massive volumes of natural language data and the social sciences continue to learn how to best make use of this new information and the technology available for analyzing it. Text Mining brings together a broad range of contemporary qualitative and quantitative methods to provide strategic and practical guidance on analyzing large text collections. This accessible book, written by a sociologist and a computer scientist, surveys the fast-changing landscape of data sources, programming languages, software packages, and methods of analysis available today. Suitable for novice and experienced researchers alike, the book will help readers use text mining techniques more efficiently and productively.


Available with
 Perusall—an eBook that makes it easier to prepare for class
Perusall is an award-winning eBook platform featuring social annotation tools that allow students and instructors to collaboratively mark up and discuss their SAGE textbook. Backed by research and supported by technological innovations developed at Harvard University, this process of learning through collaborative annotation keeps your students engaged and makes teaching easier and more effective. Learn more

 
Part I: Digital Texts, Digital Social Science
 
1. Social Science and the Digital Text Revolution
Learning Objectives

 
Introduction

 
History of Text Analysis

 
Risk and Rewards of Text Mining for the Social Sciences

 
Social Data from Digital Environments

 
Theory and Metatheory

 
Ethics of Text Mining

 
Organization of This Volume

 
 
2. Research Design Strategies
Learning Objectives

 
Introduction

 
Levels of Analysis

 
Strategies for Document Selection and Sampling

 
Types of Inferential Logic

 
Approaches to Research Design

 
Part II: Text Mining Fundamentals

 
 
3. Web Crawling and Scraping
Learning Objectives

 
Introduction

 
Web Statistics

 
Web Crawling

 
Web Scraping

 
Software for Web Crawling and Scraping

 
 
4. Lexical Resources
Learning Objectives

 
Introduction

 
WordNet

 
Roget's Thesaurus

 
Linguistic Inquiry and Word Count

 
General Inquirer

 
Wikipedia

 
Downloadable Lexical Resources and APIs

 
 
5. Basic Text Processing
Learning Objectives

 
Introduction

 
Tokenization

 
Stopword Removal

 
Stemming and Lemmatization

 
Text Statistics

 
Language Models

 
Other Text Processing

 
Software for Text Processing

 
 
6. Supervised Learning
Learning Objectives

 
Feature Representation and Weighting

 
Supervised Learning Algorithms

 
Evaluation of Supervised Learning

 
Software for Supervised Learning

 
 
Part III: Text Analysis Methods from the Humanities and Social Sciences
 
7. Thematic Analysis, QDAS, and Visualization
Learning Objectives

 
Thematic Analysis

 
Qualitative Data Analysis Software

 
Visualization Tools

 
 
8. Narrative Analysis
Learning Objectives

 
Introduction

 
Conceptual Foundations

 
Mixed Methods of Narrative Analysis

 
Automated Approaches to Narrative Analysis

 
Future Directions

 
Specialized Software for Narrative Analysis

 
 
9. Metaphor Analysis
Learning Objectives

 
Introduction

 
Theoretical Foundations

 
Qualitative Metaphor Analysis

 
Mixed Methods of Metaphor Analysis

 
Automated Metaphor Identification Methods

 
Software for Metaphor Analysis

 
 
Part IV: Text Mining Methods from Computer Science
 
10. Word and Text Relatedness
Learning Objectives

 
Introduction

 
Theoretical Foundations

 
Corpus-based and Knowledge-based Measures of Relatedness

 
Software and Datasets for Word and Text Relatedness

 
Further Reading

 
 
11. Text Classification
Learning Objectives

 
Introduction

 
Applications of Text Classification

 
Representing Texts for Supervised Text Classification

 
Text Classification Algorithms

 
Bootstrapping in Text Classifcation

 
Evaluation of Text Classification

 
Software and Datasets for Text Classification

 
 
12. Information Extraction
Learning Objectives

 
Introduction

 
Entity Extraction

 
Relation Extraction

 
Web Information Extraction

 
Template Filling

 
Software and Datasets for Information Extraction and Text Mining

 
 
13. Information Retrieval
Learning Objectives

 
Introduction

 
Theoretical Foundations

 
Components of an Information Retrieval System

 
Information Retrieval Models

 
The Vector-Space Model

 
Evaluation of Information Retrieval Models

 
Web-Based Information Retrieval

 
Software and Datasets for Information Retrieval

 
 
14. Sentiment Analysis
Learning Objectives

 
Introduction

 
Theoretical Foundations

 
Lexicons

 
Corpora

 
Tools

 
Future Directions

 
Software and Datasets for Word and Text Relatedness

 
 
15. Topic Models
Learning Objectives

 
Introduction

 
Digital Humanities

 
Political Science

 
Sociology

 
Software for Topic Modeling

 
 
V: Conclusions
 
16. Text Mining, Text Analysis, and the Future of Social Science
Introduction

 
Social and Computer Science Collaboration

 

Supplements

Student Resource Site

Visit the companion website for free access to data files and links to web resources.

Text Mining and Analysis is a comprehensive book that deals with the latest developments of text mining research, methodology, and applications. An excellent choice for anyone who wants to learn how these emerging practices can benefit their own research in an era of Big Data.

Kenneth C. C. Yang
The University of Texas at El Paso

This is a clear, comprehensive and thorough description of new text mining techniques and their applications: a "must" for students and social researchers who wish to understand how to tackle the challenges raised by Big Data.

Aude Bicquelet
London School of Economics

Clear presentation of text mining best practices. It also calls attention to the need to develop complex interpretation strategies for data acquired through various mining practices.

Mr Elias Ortega-Aponte
Graduate Division of Religion, Drew University
September 9, 2016

Never received the review copy.

Dr Babette Protz
Humanities Division, Univ Of S Carolina-Lancaster
December 16, 2015

Sample Materials & Chapters

Chapter 3

Chapter 9


Gabe Ignatow

Gabe Ignatow is Professor of Sociology and Director of Graduate Studies at the University of North Texas. His research interests are mainly in the areas of sociological theory, digital research methods, cognitive social science, and the philosophy of social science. His most recent books are Text Mining and An Introduction to Text Mining, both coauthored with Rada Mihalcea (University of Michigan). He is also a coeditor, with Wayne Brekhus (University of Missouri), of the Oxford Handbook of Cognitive Sociology. More About Author

Rada F. Mihalcea

Rada Mihalcea is a professor of computer science and engineering at the University of Michigan. Her research interests are in computational linguistics, with a focus on lexical semantics, multilingual natural language processing, and computational social sciences. She serves or has served on the editorial boards of the following journals: Computational Linguistics, Language Resources and Evaluation, Natural Language Engineering, Research on Language and Computation, IEEE Transactions on Affective Computing, and Transactions of the Association for Computational Linguistics. She was a general... More About Author

Purchasing options

Please select a format:

ISBN: 9781483369341
$95.00

SAGE Research Methods is a research methods tool created to help researchers, faculty and students with their research projects. SAGE Research Methods links over 175,000 pages of SAGE’s renowned book, journal and reference content with truly advanced search and discovery tools. Researchers can explore methods concepts to help them design research projects, understand particular methods or identify a new method, conduct their research, and write up their findings. Since SAGE Research Methods focuses on methodology rather than disciplines, it can be used across the social sciences, health sciences, and more.