Decoding Visual Sentiment of Political Imagery
This addresses label ambiguity in visual sentiment analysis for political imagery, offering a more accurate reflection of human sentiments, though it is incremental in applying existing methods to a new domain-specific challenge.
The study tackled the problem of visual sentiment analysis when viewers have systematic disagreements by integrating attitudinal differences into classification, using a dataset reflecting partisan divides and a deep learning model to predict sentiment from different ideological viewpoints, achieving improved accuracy in predictions for immigration-related images.
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.