Uncertainty-Oriented Textual Marker Selection for Extracting Relevant Terms from Job Offers - Archive ouverte HAL
Communication Dans Un Congrès Année : 2022

Uncertainty-Oriented Textual Marker Selection for Extracting Relevant Terms from Job Offers

Résumé

Automated resume ranking aims at selecting and sorting pertinent resumes, among those sent to answer a given job offer. Most of the screening and elimination process relies on the resumes’ content, marginally including information of the job offer. In this sense, currently available resume ranking approaches lack of accuracy in detecting relevant information in job offers, which is imperative to assure that selected resumes are pertinent. To improve the extraction of relevant terms that represent significant information in job offers, we study the uncertainty-oriented selection of 16 textual markers – 10 obtained by examining the behaviour of expert recruiters and 6 from the literature – according to two approaches: fuzzy logistic regression and fuzzy decision trees. Results indicate that globally, fuzzy decision trees improve the F1 and recall metrics, by 27% and 53% respectively, compared to a state-of-the-art term extraction approach.
Fichier principal
Vignette du fichier
AIFZ_2022_Published.pdf (436.72 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-04600062 , version 1 (04-06-2024)

Licence

Identifiants

Citer

Albeiro Espinal, Yannis Haralambous, Dominique Bedart, John Puentes. Uncertainty-Oriented Textual Marker Selection for Extracting Relevant Terms from Job Offers. 8th International Conference on Artificial Intelligence and Fuzzy Logic Systems, Computer Science & Information Technology, Sep 2022, Toronto, Canada. pp.01-16, ⟨10.5121/csit.2022.121601⟩. ⟨hal-04600062⟩
17 Consultations
11 Téléchargements

Altmetric

Partager

More