Learning to See: Convolutional Neural Networks for the Analysis of Social Science Data
- 16 April 2021
- journal article
- research article
- Published by Cambridge University Press (CUP) in Political Analysis
- Vol. 30 (1) , 113-131
Abstract
We provide an introduction of the functioning, implementation, and challenges of convolutional neural networks (CNNs) to classify visual information in social sciences. This tool can help scholars to make more efficient the tedious task of classifying images and extracting information from them. We illustrate the implementation and impact of this methodology by coding handwritten information from vote tallies. Our paper not only demonstrates the contributions of CNNs to both scholars and policy practitioners, but also presents the practical challenges and limitations of the method, providing advice on how to deal with these issues.Keywords
This publication has 31 references indexed in Scilit:
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images2015
- Birds of the Same Feather Tweet Together: Bayesian Ideal Point Estimation Using Twitter DataPolitical Analysis, 2015
- Active Learning by Querying Informative and Representative ExamplesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Return of the Devil in the Details: Delving Deep into Convolutional Nets2014
- Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political TextsPolitical Analysis, 2013
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Word Spotting in Archive Documents Using Shape ContextsLecture Notes in Computer Science, 2007
- Access by content to handwritten archive documents: generic document recognition method and platform for annotationsInternational Journal on Document Analysis and Recognition (IJDAR), 2007
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- Learning representations by back-propagating errorsNature, 1986