The article substantiates the possibility of involving the population to participate in improving the quality of the urban environment in the context of digital transformation. The study was carried out within the framework of the "Digital City" or "Smart City" concept, which is aimed at solving numerous problems of rapidly growing cities and cities with a large population. The article considers the possibilities of collecting and evaluating the opinion of the population from unofficial sources of information, namely social networks. Currently, this approach is used extremely limited due to the high costs of involving groups of analysts in the assessment. In the modern world, the most important role is played by the social space on the Internet. Notably, the most popular online resources are social networks. Sentiment analysis or text tonality analysis is designed for automated identification of emotionally colored vocabulary in texts and emotional evaluation of authors (opinions) in relation to the objects referred to in the text. The method has a great potential for application for monitoring, analytical and signaling systems, for document management systems and advertising platforms targeted by the subject of web pages. The process of monitoring the collection and processing of opinions of the population about the quality of life begins with forming an opinion about the quality of life and urban services of a citizen in interaction with urban infrastructure, be it public transport, healthcare, education, housing and communal services, ecology and others. Analyzing this information, it is possible to form a better modernization policy. A model for emotional tonality analysis model makes it possible to expand the capabilities of assessment tools used for managerial decision-making by involving the population in issues of urban environment management. As a result of the program implementation of the model for collecting and analyzing emotional tonality, actively discussed topics on improving the quality of the urban environment were analyzed. Variants of estimates are obtained. At the same time, processing of these data, for example, sentiment analysis, can yield refined estimates of indicators for the quality of life of the population.