INSIGHTS FROM IT JOBS MARKET WITH TEXT MINING APPROACH

摘要

On the labor market, IT Jobs represent one of the most important domains. This paper analyzed the IT Jobs from a large collection of job listings from a Romanian website. The Web Crawling techniques were used to extract the data from the website, the Text Mining, World Cloud and statistic techniques to analyze and present the results. Insights that are required for an IT Job were extracted. The results highlight the following: the most required IT Job Type was the Full Time one, the Career Level was the Mid Level and the Study Level was the Graduated one. The Text Mining Approach revealed that the most frequent words for the IT Jobs offers were: team, work, development, project, experience, environment, service, skill, customer, knowledge and software. A comparison between terms in IT Jobs in English language versus IT Jobs in Romanian language was also performed. As conclusion, in this paper, by combining different techniques to extract and analyze the textual data set of vacancy offers knowledge from the IT Jobs domain was determined and discovered. The extracted information presented insights in current skills, personal needs, career paths of the Romanian current IT labor market needs. The results of this research could be valuable information for public bodies, employers, higher education policy makers, researchers, students and parents.