Titulo Estágio
Candidates fit for Jobs
Área Tecnológica
Sistemas de Informação
Local do Estágio
DEI-FCTUC
Enquadramento
In the current context of increasing unemployment rate and competencies of unemployed people not being in use it is important to provide solutions to candidates to find jobs where they feel valued. Recruiters have traditional platforms to advertise job offers (for example their own platforms or dedicated portals), however social networks such as Facebook and LinkedIn are growingly used to advertise job offers. Hence, it could be socially worthy to integrate these processes and provide matching services between job offers an applicant curriculum vitae.
In this work it is intended to promote the interconnection between recruiters and job applicants by creating a platform that integrates the different sources of job offers, such as related information collected from social networks and from portals dedicated to the recruitment activity. This platform is intended to match job offers with applicant competencies and to recommend offers to job applicants. The platform should also manage the crawl of the web for job offers and descriptions of applicant competencies.
For this, it is intended to describe recruitment business services using [url=http://www.linked-usdl.org/]Linked USDL[/url] [1], which intends to associate semantics to business services, described with USDL [2, 3]. Linked USDL promoters want this semantics-oriented USDL version to be built upon the Linked Data (LD) principles, which enable to create typed links between data from different Web sources resulting in a web of things in the world, described by data on the Web. Since Linked USDL will provide a business perspective description of services combined with semantics, end-users will achieve a higher precision and recall during their search for services.
It is desirable to extend, reuse and/or adapt the related existing work [4] such as Human Resources Management Ontologies [5, 6] and [url=http://linkeddata.org/]Linked Open Data[/url] and to define adequate or reuse existing linked data [7], for instance [url=http://www.geonames.org/]GeoNames[/url] geographical database and Public Data Sets [8, 9].
The work will also explore the usage of multi-criteria [10] and/or economic matching mechanisms to the problem, studying and possibly applying and/or adapting the state-of-the-art to the current application case.
References
[1] C. Pedrinaci and J. Domingue, Toward the Next Wave of Services: Linked Services for the Web of Data. In Journal of Universal Computer Science, vol. 16, no. 3, pp. 1694 -1719, 2010, http://oro.open.ac.uk/23073/1/services-for-the-web-of-data.pdf
[2] Cardoso, J.; Barros, A.; May, N. and Kylau, U. Towards a Unified Service Description Language for the Internet of Services: Requirements and First Developments. In IEEE International Conference on Services Computing, IEEE Computer Society Press, Florida, USA, 2010.
[3] Cardoso, J.; Winkler, M. and Voigt, K. A Service Description Language for the Internet of Services. In First International Symposium on Services Science (ISSS'09), Leipzig, Germany, ISBN: 978-3-8325-2169-1, 2009.
[4] The Impact of Semantic Web Technologies on Job Recruitment Processes, Christian Bizer, Ralf Heese et al., http://page.mi.fu-berlin.de/mochol/papers/wi2005.pdf
[5] Human Resources Management Ontology, http://mayor2.dia.fi.upm.es/oeg-upm/index.php/en/ontologies/99-hrmontology
[6] A HUMAN RESOURCE ONTOLOGY FOR RECRUITMENT PROCESS, Volume 10, Issue 2, 2009 Review of General Management, Ionela MANIU, George MANIU, http://managementgeneral.ro/pdf/2_2009_2.pdf
[7] Linked Data Platform Use Cases and Requirements, W3C Working Draft 31 January 2013, http://www.w3.org/TR/2013/WD-ldp-ucr-20130131/
[8] IOGDS: International Open Government Dataset Search, http://logd.tw.rpi.edu/demo/international_dataset_catalog_search
[9] Public Data Sets on AWS, http://aws.amazon.com/datasets
[10] J. Figueira, S. Greco, and M. Ehrgott. Multiple Criteria Decision Analysis: State of the Art Surveys. Springer Verlag, Boston, Dordrecht, London, 2005.
Objetivo
The main objective of this MSc thesis work is to design and develop a software prototype of a platform that matches job offers with applicant competencies and recommends job offers to candidates. This platform has to integrate the different sources of job offers, such as information gathered from social networks and portals dedicated to the recruitment activity. The platform should enable to extract and automatically classify curriculum vitae. As part of this work the MSc thesis trainee should also come to open dataset models for publishing job offers and CVs.
For this, the work plan has the four main following sub-objectives:
1. Requirements analysis phase: identification of the functions the job/applicant matching/recommendation platform should perform;
2. Design phase: specification of the software architecture, as well as components, interfaces, and data storage of the prototype of job/applicant matching/recommendation platform to satisfy the specified requirements;
3. Implementation phase: programming will be used to develop and implement the prototype of job/applicant matching/recommendation platform designed in the previous phase;
4. Verification and validation phases: test cases will be defined to evaluate whether the prototype of the job/applicant matching/recommendation platform fully or partially satisfies the requirements outlined in the first phase. After testing the prototype, defects, if found, will be logged and will enable to correct the implementation. A prototype user manual will also be prepared.
Plano de Trabalhos - Semestre 1
According to the objectives explained in the previous section, this MSc thesis divides into the following tasks, each one with concrete outputs (deliverables):
Task T1: Analysis of relevant information sources such as existing job/applicant recommendation systems, social networks used for job/applicant matching/recommendation processes and of the Linked USDL language.
- When: September-October-November 2013.
- Description: Analysis of relevant information sources and familiarization with the Linked USDL
language and Linked Open Data. Identification of the adequate ontologies to reuse to semantically describe
the recruitment business services and of the suitable SPARQL-based querying mechanisms.
- Deliverables: Report indicating the relevant information sources related to recruitment business services and Human Resources Management Semantic descriptions, of the Linked USDL language and of suitable semantic web technologies. A set of recruitment business services will be selected and modeled with the Linked USDL language.
Task T2: System requirements, architecture and design.
- When: November-December 2013.
- Description: Requirements analysis. Architecture and design of the prototype of job/applicant matching/recommendation platform to develop.
- Deliverables: Report of requirements analysis and of architecture of the prototype.
Task T3: Mid-term report writing.
- When: December-January 2013-2014.
- Description: Write the report for the mid-term MSc evaluation.
- Deliverable: Mid-term MSc thesis report.
Plano de Trabalhos - Semestre 2
According to what is explained in the objectives section, the following tasks are planned for the 2nd semester:
Task T4: Implementation of the prototype of the job/applicant matching/recommendation platform.
- When: February-May 2014.
- Description: Implementation of the prototype, including SPARQL-based querying mechanisms and Multi-criteria algorithms.
- Deliverable: Prototype of the job/applicant matching/recommendation platform.
Task T5: Tests and evaluation of the prototype.
- When: May - June 2014.
- Description: Test cases will be defined and conducted to evaluate the prototype of
the job/applicant matching/recommendation platform. The prototype will be corrected if defects are found.
- Deliverables: A prototype evaluation report and a prototype user manual.
Task T6: Final MSc thesis report writing.
- When: May-July 2014.
- Description: Write final MSc thesis.
- Deliverable: MSc thesis.
Condições
This work will be carried out at DEI/Universidade de Coimbra within the Information System Group (ISG). A suitable space will be made available to the student. Meetings will be held regularly (every week) with several students working in the [url=http://genssiz.dei.uc.pt]Genssiz Center for Services Systems Research[/url].
Currently, a scholarship is not available, but we will try to provide one if possible.
Observações
This MSc thesis work will be jointly supervised by the PhD researcher Catarina Ferreira da Silva (CISUC, cferr@dei.uc.pt), the Professor Jorge Cardoso (DEI, jcardoso@dei.uc.pt, 239790051) and the Professor Paulo Melo (pmelo@fe.uc.pt).
Orientador
Catarina Ferreira da Silva / Jorge Cardoso / Paulo Melo
cferr@dei.uc.pt 📩