How can Semantic Recruitment Tools Improve Candidate Selection?

When a vacancy attracts a flood of applications, it can be difficult for HR professionals to identify the best candidates. That’s where recruitment tools can help. This study aimed to improve and refine a semantic search engine (SEM) designed to help narrow down the field.

Start & End Date

07/07/2023 - 01/07/2025

Main Applicant

van der Plas, L., IDIAP

Co-applicant(s):

• Audrin, B. EHL Hospitality Business School

• Negro Cusa, J. Arca24.com SA

External Funding

InnoSuisse

SEM24

Project Description

With rising numbers of applications per job offer, companies are finding it increasingly difficult to manage all the CVs they receive. In response to this, Swiss HR technology company Arca24 developed a semantic search engine (SEM) to extract relevant information from a CV and match candidates with job ads, with the ultimate aim of reducing the risk of timely applications being excluded and increasing the accuracy of the match between candidates and job offers. This project, carried out jointly by EHL Hospitality School, IDIAP and Arca24, aimed to address two significant challenges within the existing semantic search engine: how to ensure and improve accuracy, and how to manage the human intervention required to keep this valuable recruitment tool up to date.

Specifically, the project aimed to:

Improve recruiting automation by using deep learning to identify as-yet undiscovered information and automatically add it to the SEM, therefore increasing its efficiency and reducing the risk of excluding good candidates.
Improve accuracy by using hybrid, multilingual methods to refine the matching method to take into account soft skills as well as hard skills.
Provide key interdisciplinary insights in the fields of Natural Language Processing (NLP) , Human Resources Management (HRM) and AI in HRM, offering an interdisciplinary validation of AI tools.

Scientific Output

Vásquez-Rodríguez, L., Audrin, B., Michel, S., Galli, S., Rogenhofer, J., Negro Cusa, J., & Van Der Plas, L. (2025). A Human Perspective to AI-based Candidate Screening. In Proceedings of HICSS 58. https://scholarspace.manoa.hawaii.edu/items/ed27351f-3102-4634-ab75-d17a46e2bd5e

Vásquez-Rodríguez, L., Audrin, B., Michel, S., Galli, S., Rogenhofer, J., Negro Cusa, J., & van der Plas, L. (2024). Hardware-effective approaches for skill extraction in job offers and resumes. In Proceedings of the 4th Workshop on Recommender Systems for Human Resources (RecSysHR 2024). https://recsyshr.aau.dk/wp-content/uploads/2024/10/RecSysHR2024-paper_9.pdf

Vásquez-Rodríguez, L., Audrin, B., Michel, S., Galli, S., Rogenhofer, J., Negro Cusa, J., & van der Plas, L. (2025). Soft skills in the wild: Challenges in multilingual classification. Proceedings of the 10th edition of the Swiss Text Analytics Conference.

In the Media

Wie nutze ich KI, um meinen Traumjob zu finden? - Tages Anzeiger

Bertrand Audrin forscht zum Einsatz von KI im Bewerbungsprozess. Er kennt die neusten Entwicklungen und verrät, wie man die Spielregeln der digitalen Rekrutierung erlernt.

Read full article

EHL Blog Insights

AI in Hiring – The Case of Applicant Tracking Systems

In recent years, the increasing use of artificial intelligence has transformed many stages of the hiring process. Among these recruitment tools, Applicant Tracking Systems (ATS) have become particularly widespread, offering organizations a way to manage high numbers of applications more systematically. These systems are designed to streamline recruitment by filtering and ranking candidates, but their growing influence also raises considerations regarding their reliability and limitations for both recruiters and job seekers. Can all the qualities that make someone suitable for a role really be captured by such systems?

Read full article

Our Team

Dr. Bertrand Audrin

Assistant Professor

Dr. Bertrand Audrin is assistant professor in Human Resource Management and Organizational Behavior at EHL Business School. His research focuses on digital transformation and its impact on organizations, human resource management, and employment relationships. His current projects tackle questions on digital skills and emotional intelligence, new ways of working and AI for recruitment.

Julneth Rogenhofer

Research Assistant

Julneth Rogenhofer is a Research Assistant at EHL Hospitality Business School. Her research interests include sustainable business models in the food service industry, exploratory research methodologies, and natural language processing. She has participated in different research projects focusing on sustainability transitions and training, leading to her participation in various international conferences and writing academic and media articles.