Postdoctoral/ RD engineer position – social networks analysis and recommendation

Social Network Analysis and Recommendation


Postdoctoral, Research Scientist position




Limited term contract : 1-year initial contract with possible extension

Deadline :  15 February 2012

Position: to start as soon as possible

Research Lab : Telecom Bretagne, LUSSI Department, Brest, France

Salary: > 33 500 Euros per year, depending on qualification and experience


Telecom Bretagne has an opening for a Research Scientist position to develop our Social Network Analysis (SNA) program. This position involves algorithmic theoretical studies (roughly 50%),  application development and code implementation. The successful candidate will work in collaborative projects which aim at designing, developing and applying scalable techniques to analyze large social networks where the users share contents. The work will involve social networks data mining, community detection, score computation, link prediction in order to design and develop a SNA-based Recommendation engine. The exploitation of a friendship network and the additional data (e.g. Annotation about multimedia contents, url to contents, etc.) exchanged by the users are not fully explored. Recent, but few, studies shows that SNA-based recommender systems can deal with cold-start issues and exploit the social relationships (social influence and selection) to infer similarity and predictions (see papers by Jamali et al., Golbeck, Massa et al., Ma et al. , Yang et al., etc.).

Work will include:

  • literature review about network approaches to recommendation systems
  • design of methods and algorithms, identification of metrics, on different sets of data (e.g. geolocalized video on demand logs, Flixster sample, social shopping network); focusing on rare contents and the diversity of recommendations
  • development and integration in projects platforms (large volume data framework, e.g. Mahout, MapReduce)
  • publications


LUSSI Department at Telecom Bretagne, member of Institut Telecom and of the research Lab Labsticc (UMR CNRS), is a multidisciplinary team working on topics such as Applied Mathematics, Computer Science, Data Mining but also, Sociology, Economics, etc. Two collaborative projects (ANR VIPEER and FUI Pay2You Places) deal with SNA-based Recommender Systems, but the LUSSI department is also involved in long-term research collaborations such as a French Chair dedicated to Social Networks in eMarketing and also CominLabs (an initiative selected as part of the « Laboratoires d’Excellence » program by the French ministry of Research and education). The successful candidate will then interact with other academic partners but also industrial partners, such as Orange (telecom operator) or Crédit Mutuel (bank).


  • PhD thesis in computer science
  • Profile:  experience in social network analysis and/or recommendation systems and/or  applied mathematics
  • Interests in applied research, strong programmation skills
  • Excellent English skills, proactive attitude, ability to work in a team, and reliability.
  • French speaking would be appreciated but not mandatory


Inquiries and job application (including research statement, short CV and list of publications, recommendations welcome) should be sent by e-mail to Cécile Bothorel (cecile.bothorel [at]


Cécile Bothorel
Institut TELECOM - TELECOM Bretagne
LUSSI Dept. Pièce F01 - 114A
Technopôle Brest-Iroise CS 83818
F-29238 Brest Cedex 3
Université européenne de Bretagne
tel: +33 2 29 00 12 40

Leave a Reply




You can use these HTML tags

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>

Rejoindre ResCom

Pour s'inscrire à ResCom il vous suffit d'envoyer un mail de demande d’adhésion à l'adresse avec dans l'objet de votre e-mail subscribe asr.rescom Prénom Nom.

Vous pouvez aussi joindre le comité scientifique pour toute demandes/questions à partir de la page contact.

IL est aussi conseillé de s'inscrire à la liste di GDR asr-forum.

Pour plus d'information sur les listes, regardez la page "contacts".

Une aide sur sympa est aussi disponible.