SEMANTICS-BASED ONLINE RECRUITMENT SYSTEM رسالة ماجستير

Abstract

Due to the rapid development of job markets, conventional recruitment methods are becoming insufficient. This is because employers often receive an enormous number of applications that are difficult to process and analyze manually. To address this issue, several automatic recruitment systems have been proposed. Although these systems have proved to be more effective in processing candidate resumes (i.e. CVs) and matching them to their relevant job offers, they still suffer from low precision due to limitations associated with their underlying techniques. On the one hand, traditional keyword-based matching approaches ignore the hidden semantic dimensions in the content of job offers and resumes; and consequently a large portion of the produced results is irrelevant. On the other hand, the newer semantics-based approaches are penalized by limitations of the exploited semantic resources, namely semantic knowledge incompleteness and limited domain coverage. In this thesis, we propose an automatic online recruitment system that employs multiple semantic resources to discover the otherwise-unseen semantic dimensions of resumes and job posts. Additionally, the proposed system utilizes statistical-based concept-relatedness measures to further enrich the processed content with relevant concepts that were not initially recognized by the used semantic resources. The proposed system has been instantiated and tested using real-world data gathered from various recruitment resources on the WWW. Furthermore, the effectiveness of the employed techniques has been validated in a precision-recall based empirical framework and the results were published in two well-recognized international conferences in 2015.