Abstract
The ability to analyze a single term or phrase and generate its most relevant job titles and their similarities can be beneficial for organizations and government agencies. In this paper, we propose a framework that relies on a corpus of job postings for a single term and utilizes several text mining techniques to discover insights. The main outcome resulting from the application of our framework is a matrix and clusters representing the textual similarities between the job titles. To trial our framework, we studied the term "data science" and collected a corpus that consisted of 9,439 online job postings that contained the term. Our analysis identified 12 job titles and compared their similarities, allowing us to posit several important conclusions for data science and related fields.