Abstract:This paper provides a review of the job recommender system (JRS) literature published in the past decade (2011)(2012)(2013)(2014)(2015)(2016)(2017)(2018)(2019)(2020)(2021). Compared to previous literature reviews, we put more emphasis on contributions that incorporate the temporal and reciprocal nature of job recommendations. Previous studies on JRS suggest that taking such views into account in the design of the JRS can lead to improved model performance. Also, it may lead to a more uniform distribution of ca… Show more
“…The search proposal for the number of recommendations is displayed between two updates by varying K between 5 and 10 (interval taken in the literature) for all the proposals which respectively included ( [1,5], [1,6], [1,7], [1,8], [1,9] and [1,10]), then by recovering each time the return values of the various metrics.…”
Section: Resultsmentioning
confidence: 99%
“…For Content-based JRS, we use a semantic similarity measure between the user's profile and the set of vacancies, by estimating their respective relevance for the applicant [8]. For example, of [9] proposed, as a method, the segmentation of CV (Curriculum Vitae) into sections ordered by content, for the extraction of terms representing the skills.…”
The aim of our investigation is to personalize bilateral recommendation of job-related proposals based on existing professional social networks. In a context where the points of view of job seekers and employers can be contradictory, our approach consists in trying to bring the both in a best possible matching. To this end, we propose an integration system that gives a minimum of credit to the users’ data in order to facilitate the discovery of relevant proposals based on the users’ behaviors, on the characteristics of the proposals and on possible relationships. The main contribution is the proposal of an architecture for the recommendation of profiles and job offers including social and administrative factors. The particularity of our approach lies in the freedom from the recommendation problem by using metrics proven in the literature for the estimation of similarity rates. We have used these metrics as default values to appropriate data dimensions. It emerges that, the user’s behavior is exclusively responsible for the recommendations. However, the cross-analysis of randomly generated behaviors on real profiles collected on Cameroonian sites dedicated to job offers, shows the influence of the most active users. But, for requests via the search bar (interface with the script respecting the path of our architecture) the central subject remains the user. Our current work is limited by a data set that is not very representative of changing socio-economic conditions.
“…The search proposal for the number of recommendations is displayed between two updates by varying K between 5 and 10 (interval taken in the literature) for all the proposals which respectively included ( [1,5], [1,6], [1,7], [1,8], [1,9] and [1,10]), then by recovering each time the return values of the various metrics.…”
Section: Resultsmentioning
confidence: 99%
“…For Content-based JRS, we use a semantic similarity measure between the user's profile and the set of vacancies, by estimating their respective relevance for the applicant [8]. For example, of [9] proposed, as a method, the segmentation of CV (Curriculum Vitae) into sections ordered by content, for the extraction of terms representing the skills.…”
The aim of our investigation is to personalize bilateral recommendation of job-related proposals based on existing professional social networks. In a context where the points of view of job seekers and employers can be contradictory, our approach consists in trying to bring the both in a best possible matching. To this end, we propose an integration system that gives a minimum of credit to the users’ data in order to facilitate the discovery of relevant proposals based on the users’ behaviors, on the characteristics of the proposals and on possible relationships. The main contribution is the proposal of an architecture for the recommendation of profiles and job offers including social and administrative factors. The particularity of our approach lies in the freedom from the recommendation problem by using metrics proven in the literature for the estimation of similarity rates. We have used these metrics as default values to appropriate data dimensions. It emerges that, the user’s behavior is exclusively responsible for the recommendations. However, the cross-analysis of randomly generated behaviors on real profiles collected on Cameroonian sites dedicated to job offers, shows the influence of the most active users. But, for requests via the search bar (interface with the script respecting the path of our architecture) the central subject remains the user. Our current work is limited by a data set that is not very representative of changing socio-economic conditions.
“…The job recommender system typically mirrors the methodologies of general recommender systems [4]. Content-based [15,22] and collaborative filtering [19,25] approaches are popular in academic research.…”
Section: Related Workmentioning
confidence: 99%
“…Content-based [15,22] and collaborative filtering [19,25] approaches are popular in academic research. Knowledge-based systems [13], which focus on matching and similarity in an ontology space [4,21,26], are unique to job recommendation. Recently, hybrid systems and deep neural networks have gained traction [23].…”
“…Among the most prevalent types of JRS are Content-Based JRS (CB-JRS), Collaborative Filtering JRS (CF JRS), Hybrid JRS (H-JRS), and Knowledge-Based JRS (KB JRS) [4,5]. Each type has distinct characteristics and methodologies for recommending jobs to users:…”
In the evolving realities of recruitment, the precision of job–candidate matching is crucial. This study explores the application of Zero-Shot Recommendation AI Models to enhance this matching process. Utilizing advanced pretrained models such as all-MiniLM-L6-v2 and applying similarity metrics like dot product and cosine similarity, we assessed their effectiveness in aligning job descriptions with candidate profiles. Our evaluations, based on Top-K Accuracy across various rankings, revealed a notable enhancement in matching accuracy compared to conventional methods. Specifically, the all-MiniLM-L6-v2 model with a chunk length of 768 exhibited outstanding performance, achieving a remarkable Top-1 accuracy of 3.35%, 55.45% for Top-100, and an impressive 81.11% for Top-500, establishing it as a highly effective tool for recruitment processes. This paper presents an in-depth analysis of these models, providing insights into their potential applications in real-world recruitment scenarios. Our findings highlight the capability of Zero-Shot Learning to address the dynamic requirements of the job market, offering a scalable, efficient, and adaptable solution for job–candidate matching and setting new benchmarks in recruitment efficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.