View: |
Part 1: Document Description
|
Citation |
|
---|---|
Title: |
Replication Data for: A framework for the unsupervised analysis of images |
Identification Number: |
doi:10.7910/DVN/PZYLYU |
Distributor: |
Harvard Dataverse |
Date of Distribution: |
2023-07-27 |
Version: |
1 |
Bibliographic Citation: |
Torres, Michelle, 2023, "Replication Data for: A framework for the unsupervised analysis of images", https://doi.org/10.7910/DVN/PZYLYU, Harvard Dataverse, V1 |
Citation |
|
Title: |
Replication Data for: A framework for the unsupervised analysis of images |
Identification Number: |
doi:10.7910/DVN/PZYLYU |
Authoring Entity: |
Torres, Michelle (Rice University) |
Distributor: |
Harvard Dataverse |
Access Authority: |
Torres, Michelle |
Depositor: |
Code Ocean |
Holdings Information: |
https://doi.org/10.7910/DVN/PZYLYU |
Study Scope |
|
Keywords: |
Social Sciences, visual framing, image analysis, computer vision |
Abstract: |
This article introduces to political science a framework to analyze the content of visual material through unsupervised and semi-supervised methods. It details the implementation of a tool from the computer vision field, the Bag of Visual Words, for the definition and extraction of "tokens'' that allow researchers to build an Image-Visual Word matrix which emulates the Document-Term matrix in text analysis. This reduction technique is the basis for several tools familiar to social scientists, such as topic models, that permit exploratory, and semi-supervised analysis of images. The framework has gains in transparency, interpretability, and inclusion of domain knowledge with respect to other deep learning techniques. I illustrate the scope of the BoVW by conducting a novel visual structural topic model which focuses substantively on the identification of visual frames from the pictures of the migrant caravan from Central America. |
Methodology and Processing |
|
Sources Statement |
|
Data Access |
|
Other Study Description Materials |
|
Related Publications |
|
Citation |
|
Bibliographic Citation: |
Forthcoming, Political Analysis |
Label: |
capsule-2035317 (1).zip |
Notes: |
application/zip |
Label: |
result-7c7901aa-a745-4e31-b3e9-a7d3558e3d3a.zip |
Notes: |
application/zip |