A Novel Approach for Job Mining and Trend Summarization on Social Media Posts

Abstract

In the job classification field, precise classification of jobs to profession categories is important for harmonizing job seekers with appropriate jobs. An example of such a job title classification system is an automatic text job post classification system that utilizes machine learning. Machine learning based job type classification techniques for text and related entities have been well researched in academia and have also been successfully applied in many industrial settings. Digital recruitment is a popular online method that has been widely used for attracting individuals who are seeking for career opportunities. In recent years digital recruitment is transforming from passive websites such as Monster and Career Builder.

In this paper we present a novel approach, a machine learning- based semi-supervised job title classification system. Our method leverages a varied collection of classification and techniques to tackle the challenges of designing a scalable classification system for a large taxonomy of job categories. It encompasses these techniques in cascade classification architecture. We first present the architecture of our system, which consists of a two-stage Capture with filtration and fine level classification algorithm. The paper concludes by presenting experimental results on real world live data.