Automated Visual Content Analysis (Avca) in Communication Research
A Protocol for Large Scale Image Classification with Pre-Trained Computer Vision Models
Bibliographic Data
| ID | 12971129 |
|---|---|
| Authors | Theo Araujo (0000-0002-4633-9339, University of Amsterdam, corresponding author), Irina Lock (0000-0002-0524-3330, University of Amsterdam), Bob van de Velde (University of Amsterdam) |
| Year | 2020 |
| Volume | 14 |
| Issue | 4 |
| Pages | 239-265 |
| Publication date | 2020-09-02 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Communication Methods and Measures (JOURNAL) |
| Journal identifiers | ISSN: 1931-2458 • E-ISSN: 1931-2466 |
| Publisher | Taylor & Francis (PUBLISHER • GB) |
| DOI | 10.1080/19312458.2020.1810648 |
| OpenAlex | W3082875060 |
| Language | EN |
| Citations received | 17 |
| References cited | 84 |
The increasing volume of images published online in a wide variety of contexts requires communication researchers to address this reality by analyzing visual content at a large scale. Ongoing advances in computer vision to automatically detect objects, concepts, and features in images provide a promising opportunity for communication research. We propose a research protocol for Automated Visual Content Analysis (AVCA) to enable large-scale content analysis of images. It offers inductive and deductive ways to use commercial pre-trained models for theory building in communication science. Using the example of corporations’ website images on sustainability, we show in a step-by-step fashion how to classify a large sample (N = 21,876) of images with unsupervised and supervised machine learning, as well as custom models. The possibilities and pitfalls of these approaches are discussed, ethical issues are addressed, and application examples for future communication research are detailed
Communications protocol · Data science · Human–computer interaction · Machine learning · Multimedia · Protocol (science · Sample (material · Scale (ratio · Variety (cybernetics · Visual Communication · Computational and Text Analysis Methods · Computer Science · Law in Society and Culture · Public Relations and Crisis Communication · Artificial Intelligence
Visual storytelling through the void
Promises and pitfalls of using computer vision to make inferences about landscape preferences
Computer Vision Models for Image Analysis in Advertising Research
Integrating Network Clustering Analysis and Computational Methods to Understand Communication With and About Brands
Seeing Formalism or Formal Viewing
Who is Imaged as Being Related to Climate Change? Localization and Individualization of Human Visual Images in China Search Engine
Worlds of Agents
International media coverage of the 2023 Gaza War
Promises and Pitfalls of Social Media Data Donations
Topic modeling of video and image data
Image networks and practice analysis of larger data corpora. An approach to cluster and recontextualize visual practice in social media
Images, clusters and types – Making sense of (large) image corpora and related practices in and with digital media
Indonesia–Malaysia relations from below
Automated Visual Analysis for the Study of Social Media Effects
Biophilia gratification
Face Detection, Tracking, and Classification from Large-Scale News Archives for Analysis of Key Political Figures
Seeing the Black Lives Matter Movement Through Computer Vision? An Automated Visual Analysis of News Media Images on Facebook
The general inquirer
Analyzing Media Messages
AI can be sexist and racist — it’s time to make it fair
Machine learning
A Content Analysis of the Content Analysis Literature in Organization Studies
ImageNet
The Visual Image and the Political Image
Topic Modeling as a Strategy of Inquiry in Organizational Research
The Ethics of Big Data
Taking Stock of the Toolkit
ImageNet classification with deep convolutional neural networks
Quantitative analysis of large amounts of journalistic texts using topic modelling
ImageNet Large Scale Visual Recognition Challenge
The Use of Twitter to Track Levels of Disease Activity and Public Concern in the U.S. during the Influenza A H1N1 Pandemic
Social Data
Exploring the Space of Topic Coherence Measures
Same Candidates, Different Faces
Image Themes and Frames in US Print News Stories about Climate Change
Overcoming terms of service
Taking Television Seriously
A Clearer Picture
Understanding Consumer Conversations Around Ads in a Web 2.0 World
Computer-Assisted Topic Classification for Mixed-Methods Social Science Research
Applying LDA Topic Modeling in Communication Research
Teaching the Computer to Code Frames in News
Scaling up Content Analysis
Content Analysis as a Foundation for Programmatic Research in Communication
Shifting toward a humanized perspective? Visual framing analysis of the coverage of refugees on CNN and Spiegel Online before and after the iconic photo publication of Alan Kurdi
Multimodal content analysis
When Does an Infographic Say More Than a Thousand Words
Automated Solutions for Crowd Size Estimation
Answering Mobile Surveys With Images
Corporate media work and micro-dynamics of mediatization
Using APIs for Data Collection on Social Media
Computer Vision Models to Categorize Art Collections According to the Visual Content
Contributing to Theory and Knowledge in Quantitative Communication Science
Images that Matter
Computational Research in the Post-API Age
Towards an Articulation of the Material and Visual Turn in Organization Studies
Critical Questions for Big Data
Using Supervised Machine Learning to Code Policy Issues
The Power of Political Image
Picturing the Party
The Psychological Meaning of Words
| Unique citing works | 17 |
|---|---|
| Citations per year | 3,4 |
| Citation span | 2021 - 2026 (6) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 17 |