Analysis and shortcomings of e-recruitment systems: Towards a semantics-based approach addressing knowledge incompleteness and limited domain coverage

The rapid development of the Internet has led to introducing new methods for e-recruitment and human resources management. These methods aim to systematically address the limitations of conventional recruitment procedures through incorporating natural language processing tools and semantics-based methods. In this context, for a given job post, applicant resumes (usually uploaded as free-text unstructured documents in different formats such as .pdf, .doc or .rtf) are matched/screened out using the conventional keyword-based model enriched by additional resources such as occupational categories and semantics-based techniques. Employing these techniques has proved to be effective in reducing the cost, time, and efforts required in traditional recruitment and candidate selection methods. However, bridging the skill gap - that is, the propensity to precisely detect and extract relevant skills in applicant resumes and job posts - and highlighting the hidden semantic dimensions encoded in applicant resumes are still challenging issues in the process of devising effective e-recruitment systems. This is due to the fact that resources exploited by current e-recruitment systems are obtained from generic domain-independent sources, therefore resulting in knowledge incompleteness and the lack of domain coverage. In this article, we review state-of-the-art e-recruitment approaches and highlight recent advancements in this domain. An e-recruitment framework addressing current shortcomings through the use of multiple cooperative semantic resources, feature extraction techniques and skill relatedness measures is detailed. An instantiation of the proposed framework is proposed and an experimental validation using a real-world recruitment dataset from two employment portals demonstrates the effectiveness of the proposed approach.