Elite & Mass Political Behavior

The increasing multimodality (e.g., images, videos, links) of social media data presents opportunities and challenges. But text-as-data methods continue to dominate as modes of classification, as multimodal social media data are costly to collect and label. Researchers who face a budget constraint may need to make informed decisions regarding whether to collect and label only the textual content of social media data or their full multimodal content. In this article, we develop five measures and an experimental framework to assist with these decisions. We propose five performance metrics to measure the costs and benefits of multimodal labeling: average time per post, average time per valid response, valid response rate, intercoder agreement, and classifier’s predictive power. To estimate these measures, we introduce an experimental framework to evaluate coders’ performance under text-only and multimodal labeling conditions. We illustrate the method with a tweet labeling experiment.

We estimate the effect of social media deactivation on users’ emotional state in two large randomized experiments before the 2020 U.S. election. People who deactivated Facebook for the six weeks before the election reported a 0.060 standard deviation improvement in an index of happiness, depression, and anxiety, relative to controls who deactivated for just the first of those six weeks. People who deactivated Instagram for those six weeks reported a 0.041 standard deviation improvement relative to controls. Exploratory analysis suggests the Facebook effect is driven by people over 35, while the Instagram effect is driven by women under 25.