You are in: Caribbean
Change location

You are here

Book > Textbooks > Content Analysis
Text Mining
Share
Share

Text Mining
A Guidebook for the Social Sciences

May 2016 | 208 pages | SAGE Publications, Inc
Download flyer
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

 

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
Report this review

Never received the review copy.

Dr Babette Protz
Humanities Division, Univ Of S Carolina-Lancaster
December 16, 2015
Report this review
Key features
KEY FEATURES:
  • Unique coverage of theory, metatheory, research ethics, research design, and advanced technical tools prepares social science researchers to use text mining and text analysis in their own work.
  • Guidance on research design, selecting and sampling data, and drawing inferences from data helps researchers maximize the impact of their work.
  • Coverage of fundamental tools used in text mining methodologies includes web scraping and crawling, lexical resources, text processing, and supervised learning.
  • Research from a wide range of disciplines, including anthropology, computer science, educational research, marketing, political science, psychology, and sociology, makes the book useful for researchers throughout the social sciences.
Get 30% off SAGE Campus’ online course: Introduction to Text Mining for Social Scientists
Learn from course authors, Gabe Ignatow and Rada Mihalcea, on this self-paced online course. The course takes between 6-8 hours to complete is perfect for social scientists who want to gain a conceptual overview of the text mining landscape to take first steps towards working on a text mining project or collaborating with computational colleagues. Simply use the discount code TXTMBOOK30 at the checkout.

Sample Materials & Chapters

Chapter 3

Chapter 9