NLP-Semantic Machine Learning-Based System for Intelligent Classification of Professional Skill-Sets for Efficient Human Resource Management Process

Abstract

Skill sets can improve individual professional proficiency and enable individuals to perform better at work. Professional skill sets create opportunities to aid in advancement in job classification of individual skill advantage resulting in good human resource management to efficiently present employers with adequate and qualified candidates for a given job offer. Classifying the right people for the right skills is a common task in human resource management. This research work presents a mechanism for classifying individual extracted Summary page texts of Curriculum Vitae (CV) through the application of the Semantic Machine Learning Model. First, data was gathered by mining different summary page curriculum vitae both online and offline. Second, preprocessing of datasets, by undergoing data cleaning, text normalization, and feature extraction and splitting data sets into training and test sets in the ratio of 80:20% for train and test set. Thirdly, exploratory data analysis was carried out to visualize different variables to determine how each metrics (parameter) interact with each other regarding Skill Sets classification based on the five topics concerns (Goal Oriented, Emotional Intelligence, Good Communication Skills, Problem Solving, and Leadership skills). Fourthly, Using an Artificial Neural Network for the classification of the text vectors, ANN gave an accuracy of 94% on the 10-epoch used in the model. Performance evaluation on the model was carried out and results show a precision of 82%, 76%, 40%, 66%, and 57 % respectively for Goal Oriented, Emotional Intelligence, Good Communication Skills, Problem Solving, and Leadership skills classifications. The proposed system served as an efficient Human resource management process.