ONLINE JOB PORTAL USING NLP AND BERT FOR INTELLIGENT RECRUITMENT

The transition from academic education to professional employment remains a major challenge for college students, primarily due to the mismatch between graduate skill sets and employer expectations. Conventional job portals depend heavily on manual resume screening and keyword-based search mechanisms, which often fail to capture the contextual meaning of candidate profiles and job descriptions. As a result, these platforms frequently produce irrelevant matches, increase recruitment time, and reduce overall efficiency for both job seekers and employers. This paper proposes an intelligent online job portal tailored specifically for college students by leveraging advanced Natural Language Processing (NLP) techniques and the Bidirectional Encoder Representations from Transformers (BERT) model. The proposed system performs automated semantic analysis of resumes and job descriptions to extract skills, qualifications, and experience in a context-aware manner. By converting textual information into high-dimensional embeddings, the system enables accurate candidate–job similarity computation and ranking. In addition, an automated notification module delivers real-time alerts to eligible candidates, improving engagement and reducing missed opportunities. Experimental evaluation demonstrates that the proposed framework achieves higher precision, recall, and matching accuracy compared to traditional keyword-based recruitment systems. User feedback further indicates improved usability, relevance of recommendations, and overall satisfaction. The findings confirm that transformer-based NLP models can significantly enhance recruitment automation and provide a scalable solution for modern employment platforms, particularly for early-career job seekers.