E-Gen: Automatic Job Offer Processing System for Human Resources

Abstract

Abstract. The exponential growth of the Internet has allowed the development of a market of on-line job search sites. This paper aims at presenting the E-Gen system (Automatic Job Offer Processing system for Human Resources). E-Gen will implement two complex tasks: an analysis and categorisation of job postings, which are unstructured text documents (e-mails of job listings possibly with an attached document), an analysis and a relevance ranking of the candidate answers (cover letter and curriculum vitae). This paper aims to present a strategy to resolve the first task: after a process of filtering and lemmatisation, we use vectorial representation before generating a classification with Support Vector Machines. This first classification is afterwards transmitted to a �correc-tive� post-process which improves the quality of the solution. � IntroductionThe exponential growth of the Internet has allowed the developement of an online job-search sites market [1][2][3]. The mass of information obtained through candidate response represents a lot of information that is difficult for companies to manage [4][5][6]. It is therefore indispensable to process this information by an automatic or assisted way. The Laboratoire Informatique d'�vignon (LIA) and Aktor Interactive have developed the E-Gen system in order to resolve this problem. It will be composed of two main modules: 1. A module to extract information from a corpora of e-mails containing job descriptions. 2. A module to analyse and compute a relevance ranking of the candidate answers (cover letter and curriculum vitae).In order to extract useful information, the system analyses the contents of the e-mails containing job descriptions. In this step, there are many difficulties and �� Corresponding author.

A hybrid approach to managing job offers and candidates

“…A categorization of text segments (preamble, skills or profile, mission) is obtained by using a SVM classifier (Fan, Chen, & Lin, 2005). This preliminary classification is then transmitted to a ''corrective'' post-process which improves the quality of the solution (Module 1, described in Kessler et al, 2007). Preliminary experiments showed that segment categorization without segment position in job posting is not enough and may be a source of errors.…”

“…Our first work (Kessler, Torres-Moreno, & El-Bèze, 2007) presented the first module: the identification of different parts of a job offer and the extraction of relevant information (type of contract, salary, localization, etc.). The second module analyses the content of a candidate's e-mail, using a combination of rules and machine learning methods (Support Vector Machines, SVM) and was presented in Kessler, Torres-Moreno, and El-Bèze (2008b).…”

MatchingSem: Online recruitment system based on multiple semantic resources

“…Other systems such as E-Gen [13] have automated the recruitment process through categorizing job posts using vectorial and probabilistic models. In this context, Support Vector Machine (SVM) classification algorithms are used in order to annotate segments of job posts with the appropriate topics and features.…”

“…In this context, Support Vector Machine (SVM) classification algorithms are used in order to annotate segments of job posts with the appropriate topics and features. The main limitation of these approaches is that are subjective to high error rates since they depend on manually developed training corpora [13].…”

Automatic Profiling System for Ranking Candidates Answers in Human Resources

“…Our previous works present the first module [7], the identification of different parts of a job offer and the second module [8] which analyses the contents of a candidate e-mail with Support Vector Machine [9] and n-gramms approach. We present in this paper a strategy to resolve the last module.…”