Analyzing the association between emotions and socioeconomic characteristics of census tracts via user‐generated content

Abstract Environmental and socioeconomic characteristics of places continuously influence human emotions. To understand the quality of human life, human emotions must be effectively evaluated and their connections with socioeconomic characteristics must be determined. Social computing tools can extract emotional information from massive user‐generated content (UGC); thus, we proposed an approach that correlates residents' emotions with the socioeconomic characteristics of place based on census tracts from New York State. First, demographic and economic characteristic data from census tracts were obtained and clustered; then, an emotion recognition technique extracted human emotions quantitatively from the UGC. Applying the Apriori algorithm and logistic regression analysis showed that the socioeconomic characteristics that may significantly influence residents’ emotions include family situation, race, and economic status. Local policymakers can use the proposed approach to compare the quality of human life in different regions over a large scale via UGC and identify socioeconomic characteristics to formulate policies to improve residents’ well‐being and welfare.