TWO STAGE JOB TITLE IDENTIFICATION SYSTEM FOR ONLINE JOB ADVERTISEMENT

Abstract

The increasing volume of online job advertisements has created a need for efficient and automated methods to extract meaningful information such as job titles from unstructured text. This project proposes a two-stage job title identification system that combines rule-based and machine learning techniques to improve classification accuracy. In the first stage, job descriptions are categorized into broad domains using keyword-based classification. In the second stage, a machine learning model analyzes the processed text to predict the exact job title. This hierarchical approach reduces ambiguity and enhances prediction performance compared to single-stage systems. The proposed system is scalable, efficient, and suitable for real-world recruitment platforms, contributing to improved job matching and labor market analysis.