Title: A language model-based approach for candidates with PhD profiling in a recruiting setting

Authors: Stefania Marrara; Antonia Azzini; Nicola Cortesi

Addresses: Cefriel, Viale Sarca 226, 20126 Milano (MI), Italy ' Consortium for Technology Transfer C2T, Corso di Porta Vittoria 28, 20122, Milano, Italy ' Consortium for Technology Transfer C2T, Corso di Porta Vittoria 28, 20122, Milano, Italy; Department of Management, Information and Production Engineering, University of Bergamo, Via Pasubio, 3, 24044 Dalmine (BG), Italy

Abstract: In the last decade, students facing a PhD course in Europe find terrible difficulties in reaching a permanent position in the academy. The situation gets worse when graduated PhDs have to migrate to public/private organisations that are not always ready to understand and improve the research experience. In such a situation, one of the most critical aspects is encountered immediately in the recruitment phase, since the keywords used in job offers portals are based on the employers' vocabulary and usually do not match the words that a researcher would use to describe her/his experience. Therefore, it is widely recognised that there is a need to define a system that can support a recruiters team in recruiting PhDs. The approach presented in this paper aims at designing a decision support tool able to guide the choices of recruiter of any company in the evaluation of profiles of candidates with PhD.

Keywords: language models; knowledge management; skills profiling; job recruitment systems; knowledge extraction; information retrieval; taxonomy definition; hard skills; soft skills; profile recommendation.

DOI: 10.1504/IJWET.2020.114031

International Journal of Web Engineering and Technology, 2020 Vol.15 No.4, pp.407 - 436

Received: 08 May 2021
Accepted: 12 May 2021

Published online: 22 Mar 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article