• natural language processing
• nlp
• Rstudio
• text mining

Toscana Open Research is a project which aims to examine the alignment between the university education and the labour market requirements in Tuscany, analysing textual data coming from exams syllabuses and job vacancies. The thesis describes all the procedures carried out during the project, giving a particular attention to the data analysis and to the development of an innovative Natural Language Processing approach used for the automatic extraction of job competencies from texts. Furthermore, it includes a visualisation of a relevant part of the project’s results and some discussions about the gaps between university education and job requirements. The results of the study provide the client of the project with useful information regarding the regional situation of the demand and supply of job competencies, which can be a solid and objective base for a process of decision-making aimed at improving the educative system.