A LINGUISTIC ANALYSIS OF CORPORATE SPEAK IN JOB DESCRIPTION USING NLP

Abstract

Corporate speak poses a significant challenge to clear communication in recruitment, creating barriers for job seekers and reducing the effectiveness of job postings. In this study, we present a web-based corporate speak detection system utilizing machine learning techniques, specifically leveraging TF-IDF feature extraction combined with multiple classification algorithms. The objective is to create a robust and efficient solution capable of real-time corporate jargon detection in job descriptions. The proposed system capitalizes on the powerful capabilities of Linear Support Vector Machine (SVM), a state-of-the-art text classification algorithm, known for its accuracy and generalization in high-dimensional feature spaces. By training the model on a comprehensive dataset of 29,988 job postings from Monster.com, labeled using a lexicon of 73 corporate phrases, we optimized the classifier to accurately identify and categorize corporate speak as generic HR terms, buzzwords, or clichés. The system achieved exceptional performance with 93.11% accuracy, 95.19% precision, 96.81% recall, and 99.35% Average Precision. Additionally, to ensure the practicality and accessibility of the solution, the trained model was integrated into a Streamlit web application. This application provides a user-friendly interface for HR professionals, recruiters, and job seekers, enabling real-time corporate speak analysis with interactive visualizations, phrase highlighting, and comprehensive metrics commonly accessed through web browsers.