Studying Patterns of Behavior Profiles in Companies: A Machine Learning Approach for Classifying Archetypes in Texts

An individual’s textual productions can leave marks that help in identifying an archetype. Knowing an individual’s archetype can help you in different areas of your life, both personal and professional. In the professional field, identifying an individual’s archetype can help place him in the right company. Furthermore, for a company, identifying the archetype of employees and future employees is essential for better management, which is why this area has been demanding more and more investment and technology. In this work, we seek to identify the archetype of individuals within the business environment based on their curriculum texts. Three main approaches were made, multi-class classification, binary classification and binary regression. Focusing on identifying the archetypes related to PACE (Planner, Analyst, Communicator, and Executor), a methodology for identifying individual archetypes. For this, we use a dataset of 26,636 curriculum to apply our models. The results show potential in the identification of archetypes, obtaining an accuracy of 63% to 65% in our binary classification.