DC Field | Value | Language |
dc.contributor.author | HAMDI, ASma | - |
dc.date.accessioned | 2023-10-19T14:11:12Z | - |
dc.date.available | 2023-10-19T14:11:12Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | https://repository.esi-sba.dz/jspui/handle/123456789/576 | - |
dc.description | Supervisor : MAHAMMED Nadir / Co-supervisor : SAIDI Imene | en_US |
dc.description.abstract | Abstract :
Resume screening is a critical component of the recruitment process, enabling the identification
of qualified candidates for a given role. Advancements in technology have introduced
AI-driven approaches to enhance resume screening through natural language processing
(NLP) and machine learning algorithms.
AI resume screening utilizes various techniques to analyze resumes and cover letters.
Keyword matching involves scanning documents for keywords that match job requirements,
quickly identifying candidates with the necessary skills and qualifications. Sentiment analysis,
using NLP.
Qualification matching employs machine learning algorithms to analyze educational
backgrounds and work experiences, determining if candidates meet minimum qualifications.
Objective scoring assigns scores based on the degree of match between candidates
and job requirements, facilitating efficient prioritization of qualified candidates for further
review.
By leveraging AI and techniques such as keyword matching, sentiment analysis, qualification
matching, and objective scoring, organizations can optimize their resume screening
processes. These AI-driven methods streamline candidate evaluation, improve efficiency,
and enhance the overall effectiveness of recruitment processes.***
Résumé :
La s´election des CV est un ´el´ement essentiel du processus de recrutement, permettant
d’identifier les candidats qualifi´es pour un poste donn´e. Les avanc´ees technologiques ont
introduit des approches bas´ees sur l’intelligence artificielle pour am´eliorer la s´election des
CV grˆace au traitement du langage naturel (NLP) et aux algorithmes d’apprentissage
automatique.
La s´election automatis´ee des CV utilise diverses techniques pour analyser les CV et les
lettres de motivation. La correspondance des mots cl´es consiste `a analyser les documents `a
la recherche de mots cl´es correspondant aux exigences du poste, ce qui permet d’identifier
rapidement les candidats ayant les comp´etences et les qualifications n´ecessaires. L’analyse
de sentiment, en utilisant le NLP.
La correspondance des qualifications utilise des algorithmes d’apprentissage automatique
pour analyser les parcours ´educatifs et les exp´eriences professionnelles, afin de d´eterminer
si les candidats remplissent les qualifications minimales. L’attribution de scores
objectifs attribue des scores en fonction du degr´e de correspondance entre les candidats
et les exigences du poste, facilitant la priorisation efficace des candidats qualifi´es pour un
examen ult´erieur.
En tirant parti de l’IA et de techniques telles que la correspondance des mots cl´es,
l’analyse de sentiment, la correspondance des qualifications et l’attribution de scores objectifs,
les organisations peuvent optimiser leurs processus de s´election des CV. Ces m´ethodes
bas´ees sur l’IA simplifient l’´evaluation des candidats, am´eliorent l’efficacit´e et renforcent
l’efficacit´e globale des processus de recrutement. | en_US |
dc.language.iso | en | en_US |
dc.subject | Resume Screening | en_US |
dc.subject | Recruitment with AI | en_US |
dc.subject | Machine Learning | en_US |
dc.subject | NLP | en_US |
dc.subject | Keyword Matching | en_US |
dc.subject | Sentiment Analysis | en_US |
dc.title | Resume Screening Using NLP and Machine Learning | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | Master
|