Guardat en:
| Autors principals: | , |
|---|---|
| Format: | Recurso digital |
| Idioma: | anglès |
| Publicat: |
Zenodo
2026
|
| Matèries: | |
| Accés en línia: | https://doi.org/10.5281/zenodo.18447635 |
| Etiquetes: |
Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
Taula de continguts:
- <p><span>Inflation in resumes has been a major issue in recruitment, and in most cases, a candidate can exaggerate his technical expertise without any proof. The conventional screening </span><span>process relies heavily on self-reported skills, which results in inef</span><span>fective recruitment and skill constraints. In this paper, I suggest </span><span>an AI-based model to identify skill inflation by matching resume </span><span>assertions with publicly available developer actions, such as </span><span>GitHub repositories and professional profile texts. The suggested </span><span>system is based on the principles of Natural Language Processing </span><span>(NLP) and its ability to identify purported skills in resumes </span><span>and compare them to such objective measures as repository </span><span>originality, commit frequency, and metrics of code quality. A </span><span>machine learning algorithm is utilized to categorize the resumes </span><span>as either genuine or inflated. The outcomes of experiments prove </span><span>the suggested method to be effective in detecting the differences </span><span>between alleged and proven skills, providing a scalable and </span><span>automated method for recruitment screening.</span></p>