Типологія задач машинного аналізу текстів у сучасній соціології

This article considers the possibilities of using modern methods of word processing for sociological analysis. The main focus is on three tasks that we can currently solve using computational analysis of texts: analysis of semantic proximity, modeling of themes, and sentiment analysis. The methods discussed in this article have helped us to fully automate the semantic shifts in law enforcement-related words over the past twenty years. In recent years, the methods of processing natural language have progressed so much that it allows sociologists to automatically record the semantics of texts, compare them over time, and group based on similarity. It also allows us to scale the analysis of large arrays of documents, which opens a new page in the development of content analysis, in which we are approaching the abandonment of manual coding of documents, and researchers will be able to focus on study. We demonstrated these capabilities based on the news analysis from the resource «Ukrainska Pravda» for 2001–2020. We also grouped the news on the main topics of police reports in the publication materials and analyzed whether attitudes towards it changed during its existence.