Decoding Visual Sentiment of Political Imagery

TL;DR

This study developed a dataset that reflects societal divides, such as partisan differences, heavily influence sentiment labeling, and trained a deep learning multi-task multi-class model to predict visual sentiment from different ideological viewpoints.

Abstract

How can we define visual sentiment when viewers systematically disagree on their perspectives? This study introduces a novel approach to visual sentiment analysis by integrating attitudinal differences into visual sentiment classification. Recognizing that societal divides, such as partisan differences, heavily influence sentiment labeling, we developed a dataset that reflects these divides. We then trained a deep learning multi-task multi-class model to predict visual sentiment from different ideological viewpoints. Applied to immigration-related images, our approach captures perspectives from both Democrats and Republicans. By incorporating diverse perspectives into the labeling and model training process, our strategy addresses the limitation of label ambiguity and demonstrates improved accuracy in visual sentiment predictions. Overall, our study advocates for a paradigm shift in decoding visual sentiment toward creating classifiers that more accurately reflect the sentiments generated by humans.

Figures (14)

• Figure 1: How Would You Label Visual Sentiment of These Images?
• Figure 2: Distribution of Image Evaluation Scores by Party
• Figure 3: Convolutional Neural Network
• Figure 4: Feature Maps Visualization Heatmap (example with DenseNet-169)
• Figure 5: Model Architectures