Intelligent Analysis the Text Content of Job Profiles

This paper is devoted to the research of the structural and content configuration of the IT segment of the labor market in Novosibirsk. Thus, during the research, the text content of vacance profiles in the IT segment of the labor market was analyzed through the intelligent method – clustering. The k-means is used as a clustering method, conversion of text data to vector representation was carried out using the TF-IDF frequency method. Vacancy profile data was extracted by parsing them from the Head Hunter website. As a result of the analysis, the optimal number of clusters was obtained – 20, which formed the main requirements for the candidate in the IT segment of the labor market. In addition, we also obtained 41 clusters of main duties of the employee in the IT segment of the Novosibirsk labor market. The resulting clusters can be considered as grouping targets for similar input text data, and analysis with a certain frequency will allow you to track changes in the labor market.