Due to the overwhelming volume of job applications they get, recruiters today confront a difficult task. The necessity for automatic resume evaluationResume evaluation has grown to address this problem. This study presents a thorough methodology that uses Latent Dirichlet AllocationLatent dirichlet allocation (LDA) for resume assessment and SpaCySpaCy for object detectionObject detection in answer to this need. Our goal with this analysis is to transform the hiring process by optimizing the resume evaluationResume evaluation process and making it more effective and efficient. The suggested methodology extracts important elements from resumes, such as education, experience, and skills, using Named Entity Recognition (NERNamed Entity Recognition (NER)) from SpaCySpaCy. The LDA model then uses these discovered entities to give each a topic likelihood score, producing an overall assessment of the resume. Our study not only presents a full analysis of entity detectionEntity detection along with an extensive set of evaluation criteria, in addition, concentrates on the creation of this novel method. The methodology’s results show that it can greatly improve the hiring process by assuring a more accurate assessment of candidates’ qualifications while saving time and resources. To automate resume evaluationResume evaluation, our research presents a novel approach that blends entity detectionEntity detection with LDA. This strategy can change the hiring procedure. Our research indicates that this strategy is quite promising and could help recruiters overcome the increasing difficulties they experience in the contemporary employment market.