Images As Data for Social Science Research - An Introduction to Convolutional Neural Nets for Image Classification

Zusammenfassung Shows how innovation in computer vision methods can markedly lower the costs of using images as data. Introduces readers to deep learning algorithms commonly used for object recognition, facial recognition, and visual sentiment analysis. Provides guidance and instruction for scholars interested in using these methods in their own research. Inhaltsverzeichnis 1. Introduction; 2. Prerequisites for computer vision methods and tutorials; 3. Introduction to CNNs for social scientists; 4. Overview of fine-tuning a CNN classifier for images; 5. Political science working example: images related to a Black Lives Matter protest; 6. The promise and limits of autotaggers; 7. Application: fine-tuning an open source CNN; 8. Legal and ethical concerns in using images as data; 9. Conclusion; 10. References.

Dettagli sul prodotto

• Autori: Andreu Casas, Nora Webb Williams, Nora (University of Illinois Webb Williams, John D Wilkerson, John D. Wilkerson, Wilkerson John D., Nora Webb Williams
• Editore: Cambridge University Press ELT
• Lingue: Inglese
• Formato: Tascabile
• Pubblicazione: 31.08.2020
• EAN: 9781108816854
• ISBN: 978-1-108-81685-4
• Pagine: 75
• Serie: Elements in Quantitative and C; Elements in Quantitative and Computational Methods for the Social Sciences
• Categorie: Scienze naturali, medicina, informatica, tecnica > Informatica, EDP > Comunicazione dati, reti; Scienze sociali, diritto, economia > Scienze politiche > Scienze politiche e cittadinanza attiva; Data Mining, POLITICAL SCIENCE / General, Politics & government, Politics and government, Social research & statistics, Social research and statistics, Research methods: general, Data capture and analysis, Data Capture & Analysis