HYRE-ME – Hybrid Architecture for Recommendation and Matchmaking in Employment

  • Bruno CoelhoEmail author
  • Fernando Costa
  • Gil M. Gonçalves
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 538)


Nowadays people search job opportunities or candidates mainly online, where several websites for this end already do exist (LinkedIn, Freelancer and oDesk, amongst others). This task is especially difficult because of the large number of items to look for and the need for manual compatibility verification. What we propose in this paper is a recruitment recommendation system that considers the user model (content-based filtering) and social interactions (collaborative filtering, e.g. likes and follows) to improve the quality of its suggestions. The devised solution is also able to generate adequate teams for a given job opportunity, based not only on the needed skills but also on the social compatibility between their members.


Recommender systems Decision support systems Match-making algorithms Jobs Employment Work Teams User modeling Content-based filtering Collaborative filtering 



This work has been supported by the project WorkInTeam, funded under the Portuguese National Strategic Reference Programme (QREN 2007-2013) under the contract number 2013/38566.


  1. 1.
    Blanchard, E., Harzallah, M., Briand, H., Kuntz, P.: A typology of ontology-based semantic measures. In: EMOI-INTEROP 2005 (2005)Google Scholar
  2. 2.
    Datta, A., Braghin, S., Yong, J.T.: The zen of multidisciplinary team recommendation. J. Assoc. Inf. Sci. Technol. (2013)Google Scholar
  3. 3.
    Datta, A., Yong, J.T., Ventresque, A.: T-RecS: team recommendation system through expertise. In: WWW 2011 (2011)Google Scholar
  4. 4.
    de Rond, M.: Why less is more in teams. Harvard Business Review (2012)Google Scholar
  5. 5.
    Lu, Y., Helou, S.E., Gillet, D.: A recommender system for job seeking and recruiting website. In: WWW 2013 (2013)Google Scholar
  6. 6.
    Putnam, D.: Haste makes waste when you over-staff to achieve schedule compression (2015)Google Scholar
  7. 7.
    Rauch, K.L., Scholar, M., University, P.S.: Human mate selection: an exploration of assortative (2003)Google Scholar
  8. 8.
    Ringelmann, M.: Recherches sur les moteurs animés: Travail de l’homme. In Annales de l’Institut National Agronomique (1913)Google Scholar
  9. 9.
    Sahebi, S., Cohen, W.: Community-based recommendations: a solution to the cold start problem. In: RecSys 2011 (2011)Google Scholar
  10. 10.
    Simms, A., Nichols, T.: Social loafing: a review of the literature. J. Manage. Policy Pract. (2014)Google Scholar
  11. 11.
    Smith, C.: By the numbers: 12 interesting LinkedIn job statistics (2015)Google Scholar
  12. 12.
    University, W.: Is your team too big? Too small? What’s the right number? (2006)Google Scholar
  13. 13.
    Wagner, K.: LinkedIn hits 300 million users amid mobile push (2014)Google Scholar
  14. 14.
    Widmeyer, W.N., Brawley, L., Carron, A.: The measurement of cohesion in sport teams: the group environment questionnaire (1985)Google Scholar
  15. 15.
    Yu, H., Liu, C., Zhang, F.: Reciprocal recommendation algorithm for the field of recruitment. J. Inf. Comput. Sci. 8(16), 4061–4068 (2011) Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Bruno Coelho
    • 1
    Email author
  • Fernando Costa
    • 2
  • Gil M. Gonçalves
    • 1
  1. 1.INOVA+MatosinhoPortugal
  2. 2.Instituto Superior de Engenharia Do PortoPortoPortugal

Personalised recommendations