From Manual Review to AI Automation: An NLP-Powered System for Efficient CV Processing in Academic Admissions

Abstract

Manual screening of thousands of admissions of master's program applications at Hassan II University of Casablanca is a time and labor-intensive task. Towards this challenge, we designed a machine-based solution utilizing Natural Language Processing (NLP) for summarization and CV ranking on a large set of CVs. Our solution relies on pre-trained spaCy and Hugging Face Transformers-based Named Entity Recognition (NER) models for the retrieval of information such as education, experience, and skills. We then incorporated extractive summarization by using BERT-based models for the selection of the most informative sentences and then the abstractive summarization by utilizing advanced language models such as LLAMA for the summaries to be coherent and easy. We verified our system by conducting a case study of the master's program of Big Data and Data Science by running a set of 2,325 CVs. The model gave very good results like a 72,67 % ROUGE-1 Recall, 74,32 % ROUGE-2 Recall, 73,15 % ROUGE-1 Precision, 57,28 % ROUGE-2 Precision, and 82% Named Entity Recognition (NER) Precision. The system processed a CV on average in 3,84 seconds. We also integrated a conversation bot (chatbot) that allows admissions teams to search the CVs uploaded in real time for improved decision-making effectiveness and significantly decreasing the administrative burden. The promise of NLP-driven automation stands out from this research as a scalable as well as efficient method of screening numerous applicants.