@article{3f1ab19f86504cdbbf0400c6effbae82,
title = "Visual Models for Social Media Image Analysis: Groupings, Engagement, Trends, and Rankings",
abstract = "With social media image analysis, one collects and interprets online images for the study of topical affairs. This analytical undertaking requires formats for displaying collections of images that enable their inspection. First, we discuss features of social media images to make a case for studying them in groups (rather than individually): multiplicity, circulation, modification, networkedness, and platform specificity. In all, these offer reasons and means for an approach to social media image research that privileges the collection of images as its analytical object. Second, taking the 2019 Amazon rainforest fires as a case study, we present four visual models for analyzing collections of social media images. Each visual model matches a distinctive spatial arrangement with a type of analysis: grouping images by theme with clusters, surfacing dominant images and their engagement with treemaps, following image trends with plots, and comparing image rankings across platforms with grids.",
keywords = "visual methods, social media, digital methods, data visualization, image analysis, visual culture, new media, internet studies, images, Amazon forest, forest fires, digital culture, memes",
author = "Gabriele Colombo and Liliana Bounegru and Gray, {Jonathan W. Y.}",
note = "Funding Information: The authors would like to thank the European Forest Institute for their support with this project, particularly Rina Tsubaki, who joined us in exploring online material related to the Amazon forest fires. We started delving into the case study on which this article draws through “engaged research-led teaching” projects together with postgraduate students on the Digital Methods MA module (2019–2020) in the Department of Digital Humanities, King{\textquoteright}s College London who joined us to try out a set of visual methods recipes (recipes.publicdatalab.org). We are also most grateful for feedback on different aspects of this work to participants at the “25th Digital Research in the Humanities and Arts Conference”; the “Ecologies and Infrastructures: Cultural Techniques of Environmental Management” symposium co-organized by Arizona State University and King{\textquoteright}s College London; and the Digital Ecologies research group at the University of Cambridge. Finally, we would be remiss without mentioning our network of friends and colleagues associated with the Public Data Lab who were involved in developing and testing the approaches we explore in this article. Publisher Copyright: {\textcopyright} 2023 (Gabriele Colombo, Liliana Bounegru, and Jonathan Gray). Licensed under the Creative Commons Attribution Non-commercial No Derivatives (by-nc-nd). Available at http://ijoc.org.",
year = "2023",
month = feb,
day = "28",
language = "English",
volume = "17",
pages = "1956--1983",
journal = "International Journal of Communication",
issn = "1932-8036",
publisher = "University of Southern California, Annenberg School for Communication & Journalism",
}