Analyzing job advertisements and skill descriptions using NLP techniques (part 1: data cleaning and pre-processing and part 4: front-end visualization/user interface) - collaboration with CAO

• Main Author: Dinglasan, Cris Anthony Sarmiento
• Other Authors: S Supraja
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering; Natural language processing; Machine learning; Job descriptions; Employment
• Online Access: https://hdl.handle.net/10356/176650
• Institution: Nanyang Technological University

In a competitive job market, it is imperative that people continuously stay relevant to employers. This is especially important for fresh graduates with minimal working experience, and for workers in sunsetting industries, such as traditional print media and Landline telephone services. Efforts have been made by the Government of Singapore to facilitate this upskilling and reskilling amongst Singaporeans through their support of the SkillsFuture Movement. This collaborative project aims to leverage NLP techniques and ML to analyse job advertisements and skill descriptions to help determine which skills are the most relevant for specific industries and occupations. In doing so, we hope to help equip the people in the workforce with the ability to find jobs more relevant to their skills, as well as allow them to learn what skills to develop to help them reach their career goals. My contribution to the project involves the cleaning and preprocessing of data provided by NTU's CAO, and other publicly available sources, to prepare them for use in training an ML model to determine, from a job description, what hard and soft skills are needed to perform that job, and then create a front-end user interface for visualizing and interacting with our findings.