Text Analysis in Python for Social Scientists - Prediction and Classification

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.

List of contents

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.

Summary

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.

Foreword

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

Product details

• Authors: Dirk Hovy, Dirk (Universita Commerciale Luigi Bocconi Hovy
• Publisher: Cambridge University Press ELT
• Languages: English
• Product format: Paperback / Softback
• Released: 31.12.2021
• EAN: 9781108958509
• ISBN: 978-1-108-95850-9
• No. of pages: 75
• Series: Elements in Quantitative and Computational Methods for the Social Sciences
• Subjects: Natural sciences, medicine, IT, technology > IT, data processing > IT; Social sciences, law, business > Political science > Political science and political education; COMPUTERS / Data Science / Data Analytics, Data capture and analysis, Data Capture & Analysis