Coping through Precise Labeling of Emotions: A Deep Learning Approach to Studying Emotional Granularity in Consumer Reviews

When describing their emotions, people may demonstrate emotional expertise by differentiating between emotions when using emotional labels, or use emotion labels interchangeably to indicate a general valence. The authors develop a novel deep-learning-based method to measure the granularity with which people describe their emotions via language. They examine the role of emotional granularity in consumer decision-making, particularly in how consumers rate unpleasant service experiences (e.g., service failures) in online reviews. Consistent with the notion that granularity in describing negative emotions is associated with more successful self-regulation of negative emotions, consumers who express their negative emotions more granularly in review texts tend to rate businesses less negatively following service failures. Furthermore, a greater temporal distance between an experience and describing it leads to greater granularity in describing negative emotions. Consequently, a greater temporal distance between the service experience and writing the review predicts more positive ratings following service failures. The results have implications for a) understanding the role of emotional granularity in consumer decision making; b) understanding the predictors of online review ratings, as an important category of consumer decisions; and c) profiling consumers based on emotion regulation abilities inferred from the online content they generate.