Text Mining Techniques for Automated Resume Analysis

Abstract—Resume parser is a technology used to extract and examine data from the resumes of job applicants. This project aims to automate resume screening, making it quicker and more effective for recruiters and HR departments. The method for generating similarity scores between a resume and a job description using natural language processing techniques is presented in the study. Using CountVectorizer and cosine_similarity, the method entails extracting text from uploaded files, including the education and skills sections of the résumé, and determining similarity scores. The education and skills parts are additionally categorized using a Support Vector Classification model based on similarity scores. This approach may be helpful in the world of human resources and can help match people to job opportunities