Community-Based Data Integration of Course and Job Data in Support of Personalized Career-Education Recommendations

TL;DR

This paper presents a novel community-based data integration method that links course descriptions and job ads to improve personalized career and education recommendations, supporting lifelong learning.

Contribution

It introduces a heterogeneous graph approach with skill community detection to enable cross-domain recommendations between education and employment data.

Findings

Effective integration of course and job data through community detection.

Enhanced personalized recommendations for careers and education.

Supports lifelong learning with cross-domain insights.

Abstract

How does your education impact your professional career? Ideally, the courses you take help you identify, get hired for, and perform the job you always wanted. However, not all courses provide skills that transfer to existing and future jobs; skill terms used in course descriptions might be different from those listed in job advertisements; and there might exist a considerable skill gap between what is taught in courses and what is needed for a job. In this study, we propose a novel method to integrate extensive course description and job advertisement data by leveraging heterogeneous data integration and community detection. The innovative heterogeneous graph approach along with identified skill communities enables cross-domain information recommendation, e.g., given an educational profile, job recommendations can be provided together with suggestions on education opportunities for re- and upskilling in support of lifelong learning.