Michelle Torres
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Michelle Torres has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Francisco Cantú
University of Houston, Houston, USA
2 shared publications Avidit Acharya
Cambridge University Press, One Liberty Plaza, New York, NY 0006, USA
1 shared publicationBrandon De
Cambridge University Press, Journals Fulfilment Department, One Liberty Plaza, New York, NY 0006, USA; or
1 shared publication- Bryce Jensen Dietrich
Department of Political Science Purdue University West Lafayette Indiana USA
1 shared publication - Chad Hazlett
UCLA
1 shared publication - Christopher F. Parmeter
University of Miami, Miami, USA
1 shared publication
Latest Publications
- 23 October 2023
- Published by Cambridge University Press (CUP) in Political Analysis
- Vol. 32 (2) , 199-220
A Framework for the Unsupervised and Semi-Supervised Analysis of Visual Frames
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 (BoVW), 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.
- 23 October 2023
- Published by Cambridge University Press (CUP) in Political Analysis
- Vol. 32 (2) , 199-220
A Framework for the Unsupervised and Semi-Supervised Analysis of Visual Frames
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 (BoVW), 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.
- Open Access
- 22 December 2021
- Published by Cambridge University Press (CUP) in Political Analysis
- Vol. 30 (1) , b1-b2
PAN volume 30 issue 1 Cover and Back matter
- 22 December 2021
- Published by Cambridge University Press (CUP) in Political Analysis
- Vol. 30 (1) , b1-b2
Open AccessPAN volume 30 issue 1 Cover and Back matter
- 16 April 2021
- Published by Cambridge University Press (CUP) in Political Analysis
- Vol. 30 (1) , 113-131
Learning to See: Convolutional Neural Networks for the Analysis of Social Science Data
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.
- 16 April 2021
- Published by Cambridge University Press (CUP) in Political Analysis
- Vol. 30 (1) , 113-131
Learning to See: Convolutional Neural Networks for the Analysis of Social Science Data
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.
- 13 February 2020
- Published by Cambridge University Press (CUP) in Political Science Research and Methods
- Vol. 8 (3) , 391-408
Estimating controlled direct effects through marginal structural models
When working with panel data, many researchers wish to estimate the direct effects of time-varying factors on future outcomes. However, when a baseline treatment affects both the confounders of further stages of the treatment and the outcome, the estimation of controlled direct effects (CDEs) using traditional regression methods faces a bias trade-off between confounding bias and post-treatment control. Drawing on research from the field of epidemiology, in this article I present a marginal structural modeling (MSM) approach that allows scholars to generate unbiased estimates of CDEs. Further, I detail the characteristics and implementation of MSMs, compare the performance of this approach under different conditions, and discuss and assess practical challenges when conducting them. After presenting the method, I apply MSMs to estimate the effect of wealth in childhood on political participation, highlighting the improvement in terms of bias relative to traditional regression models. The analysis shows that MSMs improve our understanding of causal mechanisms especially when dealing with multi-categorical time-varying treatments and non-continuous outcomes.
- 13 February 2020
- Published by Cambridge University Press (CUP) in Political Science Research and Methods
- Vol. 8 (3) , 391-408
Estimating controlled direct effects through marginal structural models
When working with panel data, many researchers wish to estimate the direct effects of time-varying factors on future outcomes. However, when a baseline treatment affects both the confounders of further stages of the treatment and the outcome, the estimation of controlled direct effects (CDEs) using traditional regression methods faces a bias trade-off between confounding bias and post-treatment control. Drawing on research from the field of epidemiology, in this article I present a marginal structural modeling (MSM) approach that allows scholars to generate unbiased estimates of CDEs. Further, I detail the characteristics and implementation of MSMs, compare the performance of this approach under different conditions, and discuss and assess practical challenges when conducting them. After presenting the method, I apply MSMs to estimate the effect of wealth in childhood on political participation, highlighting the improvement in terms of bias relative to traditional regression models. The analysis shows that MSMs improve our understanding of causal mechanisms especially when dealing with multi-categorical time-varying treatments and non-continuous outcomes.