Differential Hiring using a Combination of NER and Word Embedding
Suhas H E1, Manjunath A E2
1Suhas H E*, Computer Science, R V College of Engineering, Bengaluru, India.
2Manjunath A E, Computer Science, R V College of Engineering, Bengaluru, India.
Manuscript received on April 02, 2020. | Revised Manuscript received on April 21, 2020. | Manuscript published on May 30, 2020. | PP: 1344-1349 | Volume-9 Issue-1, May 2020. | Retrieval Number: A2400059120/2020©BEIESP | DOI: 10.35940/ijrte.A2400.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this data-driven world, AI is being used in almost all the tasks to automate processes and make human life more comfortable. One such industry where Artificial Intelligence (AI) importance is growing is the recruiting industry. This paper aims to propose a new and a better method to match the most suitable talent to jobs, which has been incorporated using two methods – suggesting top resumes to a job opening from a talent pool to a recruiter, recommending top jobs which match to a candidate based on the candidate’s resume. Natural Language Processing techniques have been used in implementing this approach – Named Entity Recognition (NER), Word embedding model, and Cosine similarity using which a resume and job will be matched. The NER model is used to extract useful entities from documents, which is enhanced by the word2vec model by making the system more generic and the similarity is calculated using the cosine similarity algorithm.
Keywords: Cosine Similarity, Differential Hiring, Natural language Processing, Word Embedding.
Scope of the Article: Natural language Processing