Replication Data for: Taken at Face Value: Emotion Expression and Protest Dynamics

Understanding the role of emotions in protest is a growing field of research, but existing research does not address the role of emotions once protests start. By applying computer vision models to the expressed emotions of the 37,558 faces in 7,824 geolocated protest images across twelve protest waves in ten countries, this article makes five contributions to the study of emotions and protest. Most importantly, it measures emotions within protest waves, not before them. It also investigates emotions’ temporal effects, multiple emotions simultaneously, connects them directly to actual protests, and does so across multiple countries. The results suggest that anger, disgust, fear, happiness, sadness, and surprise occur simultaneously throughout a protest, though happiness peaks on the first day. Emotions sometimes correlate with protest size in unexpected directions, and the coefficient signs differ by country. The most consistent finding is that models without lagged terms outperform those with lags, suggesting emotions and protests covary more than the former causes changes in the latter. Keywords: protest, emotions, collective action, social movements, computer vision, machine learning, violence.

探究情绪在抗议活动中的作用是日益受到关注的研究领域，但现有研究尚未覆盖抗议爆发后情绪所扮演的角色。本文针对10个国家12轮抗议浪潮中的7824张带有地理定位的抗议图像（共涵盖37558张人脸）中的面部表情情绪应用计算机视觉模型，就此在情绪与抗议研究领域做出五项贡献。尤为关键的是，本文对抗议浪潮进行期间的情绪展开测算，而非仅关注抗议爆发前的情绪状态。此外，本文同时考察情绪的时序效应、多情绪共存现象，将情绪与实际抗议活动直接关联，并实现了多国场景下的研究覆盖。研究结果显示，愤怒、厌恶、恐惧、喜悦、悲伤与惊讶六种情绪在抗议全程中均有呈现，其中喜悦情绪在抗议首日达到峰值。部分情绪与抗议规模的相关性呈现出意料之外的方向，且相关系数的符号因国家而异。本研究最一致的结论是：未引入滞后项的模型表现优于引入滞后项的模型，这表明情绪与抗议活动更多呈现共变关系，而非情绪先行引发抗议活动的变化。关键词：抗议、情绪、集体行动、社会运动、计算机视觉、机器学习、暴力。