Sistem Rekomendasi Pemilihan Pekerjaan Yang Relevan Berbasis Content-Based Filtering Dan Semantic Matching

The rapid growth of job vacancy information makes it difficult for job seekers to find positions that align with their profiles and competencies. This study aims to develop a web-based job recommendation system using Content-Based Filtering combined with a Semantic Matching approach to provide recommendations based on the compatibility between user profiles and job vacancy data. Prior to the recommendation process, text data undergoes preprocessing stages, including case folding, tokenization, stopword removal, and stemming. Subsequently, Content-Based Filtering is employed to match user profile attributes with job vacancy attributes, while Semantic Matching supports the matching process to ensure the resulting recommendations are more relevant. The system was developed using the Evolutionary Prototyping method and tested via Black Box Testing. Test results indicate that all system functions operate according to requirements and are capable of providing relevant job recommendations based on the alignment between user profiles and job vacancy data.