On The Exploitation Of Textual Descriptions For A Better-Informed Task Assignment Process

Human resources always play a crucial role on firms' profitability and sustainability. For a long time already, the identification of the appropriate personnel possessing the skills and expertise required to undertake a task is mainly performed through simple keyword searches exploiting structured data. In this paper, we build on Natural Language Processing techniques to take this identification to a higher level of detail, granularity and accuracy. Our approach elaborates unstructured data such as descriptions and titles of tasks to extract valuable information about the employees' capability of successfully engaging with a particular task. Text classifiers such as naive Bayes, logistic regression, support vector machines, k-nearest neighbors and neural networks are being tested and comparably assessed.