A Hybrid Approach to Conceptual Classification and Ranking of Resumes and Their Corresponding Job Posts

Due to the constant growth in online recruitment, job portals are starting to receive thousands of resumes in diverse styles and formats from job seekers who have different fields of expertise and specialize in various domains. Accordingly, automatically extracting structured information from such resumes is needed not only to support the automatic matching between candidate resumes and their corresponding job offers, but also to efficiently route them to their appropriate occupational categories to minimize the effort required for managing and organizing them. As a result, instead of searching globally in the entire space of resumes and job posts, resumes that fall under a certain occupational category are only those that will be matched to their relevant job post. In this research work, we present a hybrid approach that employs conceptual-based classification of resumes and job postings and automatically ranks candidate resumes (that fall under each category) to their corresponding job offers. In this context, we exploit an integrated knowledge base for carrying out the classification task and experimentally demonstrate - using a real-world recruitment dataset- achieving promising precision results compared to conventional machine learning based resume classification approaches.