Text Analysis in Python for Social Scientists
Prediction and Classification

A practical guide to text classification and neural networks in Python for social scientists.

Dirk Hovy (Author)

9781108958509, Cambridge University Press

Paperback / softback, published 17 March 2022

75 pages
22.8 x 15.1 x 0.7 cm, 0.157 kg

Text contains a wealth of information about about a wide variety of sociocultural constructs. Automated prediction methods can infer these quantities (sentiment analysis is probably the most well-known application). However, there is virtually no limit to the kinds of things we can predict from text: power, trust, misogyny, are all signaled in language. These algorithms easily scale to corpus sizes infeasible for manual analysis. Prediction algorithms have become steadily more powerful, especially with the advent of neural network methods. However, applying these techniques usually requires profound programming knowledge and machine learning expertise. As a result, many social scientists do not apply them. This Element provides the working social scientist with an overview of the most common methods for text classification, an intuition of their applicability, and Python code to execute them. It covers both the ethical foundations of such work as well as the emerging potential of neural network methods.

1. Introduction
2. Ethics, Fairness, and Bias
3. Classification
4. Text as Input
5. Labels
6. Train-Dev-Test
7. Performance Metrics
8. Comparison and Significance Testing
9. Overfitting and Regularization
10. Model Selection and Other Classifiers
11. Model Bias
12. Feature Selection
13. Structured Prediction
14. Neural Networks Background
15. Neural Architectures and Models.

Subject Areas: Political science & theory [JPA]