Latent semantic analysis (LSA)‎ and ontological concepts to support e-recruitment

Other Title(s)

التحليل الدلالي الكامن و مفاهيم الدلائل لدعم التوظيف الإلكتروني

Dissertant

al-lasassmah, Khalil Qaftan Ibrahim

Thesis advisor

Kayid, Ahmad K. A.

Comitee Members

al-Sadi, Jihad
Nasir al-Din, Hibah

University

Middle East University

Faculty

Faculty of Information Technology

Department

Computer Science Department

University Country

Jordan

Degree

Master

Degree Date

2013

English Abstract

Nowadays, supporting e-recruitment by new techniques and applications is one of the major research topics of applied semantic ontology.

Most of the latest works, in this domain, has focused on analyzing the contents of CVs and matching them with job postings in order to find the most relevant CVs to a certain job posting.

In this research, we present a new approach based on combining ontological concepts and latent semantic analysis together to match between CVs and job postings.

This research investigates building a matrix in LSA that is based on using the ontological concepts and instances instead of words that are used in the traditional approaches.

It also investigates enhancing the clustering using the concepts and instances.

Our approach is better than other approaches in the sense that it takes into account the meanings and relationships among words, and also considers different words that have same meaning and words that are semantically equivalent.

By implementing our methodology on a set of CVs and matching them with an actual job posting, and comparing our results with the results of other traditional approaches, our approach achieved 84% accuracy, which higher than all other approaches.

Main Subjects

Information Technology and Computer Science

No. of Pages

69

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-699538