Political communication is a central element of several political dynamics. Its visual component is crucial in understanding the origin, characteristics and consequences of the messages sent between political figures, media and citizens. However, visual features have been largely overlooked in Political Science. Thus, this article dissects the structure, and content of visual material, and assesses its relationship with political attitudes. More specifically, the article focuses on depictions of protests and demonstrations. In the first part of this project, I implement computer vision and image retrieval techniques to measure and understand messages conveyed in pictures.
The article presents and details the implementation of a Bag of (Visual) Words (BoVW), an intuitive and accessible technique for the extraction and quantification of visual features that allows researchers to build an Image-Visual Word (I-VW) matrix that emulates the Document-Term matrix in text analysis. For the purposes of this article, I validate the BoVW approach using a structural topic model setting to identify relevant political features of images of protests. Preliminary results show that conservative newspapers depict protests in darker and nocturnal settings more often than liberal outlets. The article introduces and illustrates the use of a useful technique for the analysis and measurement of messages in pictures.
