This paper presents the results of the social mood study of St. Petersburg citizens based on text data from the social network VKontakte. The proposed method involves juxtaposition of the social media users’ tone of discussions with quantitative data describing the city infrastructure. The comparison is possible due to the fact that text data can be tied to a region. The article substantiates the method by which the concepts “social mood” and “social well-being” are combined. Approaches to sentiment analysis of specific textual data are also described (quality metrics of the models used). The paper demonstrates the final applicable results: the data are plotted on the map of the city.