Accueil du site Accueil du site Adhésion Contact Plan du site

Social Networks and NLP

2013 Volume 54 Number 3.

Direction : Atefeh Farzindar, Mathieu Roche.


Social networks, dynamic structures comprised of individuals or organizations, have always played a major role in our societies. They have evolved and diversified with the Web 2.0, which offers users the possibility to create and share content through multiple platforms (blogs, micro-blogs, wikis, sharing sites, etc.). In this environment, the unprecedented volume and variety of textual data as well as the users’ interaction network give rise to new opportunities to better understand social behavior. The study of messages exchanged represents a new challenge in Natural Language Processing. In this context, it becomes interesting to discuss the strength of NLP methods (morphosyntactic analysers, systems of term extraction and of named entity recognition, etc.) on this data. In this special issue, new approaches will be presented for the purpose of analysing this massive, heterogeneous and usually noisy textual data coming from social networks.

In addition, these means of communication are powerful collective tools where language is both invented and experienced with. Certain words are then attributed new meanings, and the creation of words or new syntactic structures becomes widespread (for example, by mixing different languages). The creation, dissemination and processing of this original vocabulary can be discussed in this special issue, which, in a broader perspective, will highlight a new way to communicate.

Some metadata (for example, the hashtags) and the linguistic descriptors originating from texts constitute a solid base for the analysis of social networks. They bring to the fore different socio-economic, political and geographic communities, just to name a few. In addition, the linguistic descriptors, whether they are words or syntagmatic relations, allow for a precise analysis of the feelings and opinions contained in the messages. For example, the lexical, graphic and even syntactic specificities (emoticons, abbreviations, character repetition, etc.) in the text data contain valuable information allowing for the detection of opinions or analysis of feelings (fine detection of emotions, identification of irony, etc.).

Finally, this special issue will be an opportunity to describe new problems arising from social networks development. For example, systems that monitor social networks must be able to detect potential usurpers or study the dissemination of information. This special issue offers the opportunity to present original applications adapted to the processing of textual data that stems from social networks.

Non-exhaustive list of topics covered in this special issue :

-  Creation of resources (corpus, dictionaries, etc.) from social networks ;

-  Syntactic analysis of non-structured written material ;

-  Identification of named entities arising from new means of communication ;

-  Generation of words/phrases and language dynamism ;

-  Multilingualism and mixed languages ;

-  Categorization and grouping of textual data from social networks (communities, thematics, profiles, etc) ;

-  Detection of weak signals in social networks ;

-  Spreading of content and linguistic practices ;

-  Sentiment analysis/opinion mining ;

-  Contextual interpretation of the content of social networks ;

-  Extraction and indexing of textual information in social networks ;

-  Evaluation and quality of data generated from social networks ;

-  Monitoring systems ;

-  E-reputation ;

-  Detection of usurpers and avatars ;

-  Speech and dialogs analysis ;

-  Summary of activities in the networks.


Submission of abstracts : October 15, 2013

Submission of articles : October 29, 2013

First notification to authors : December 20, 2013

Submission of revised articles : February 1, 2014

Final notification : April 15, 2014

Final version : June 15, 2014


-  Abdelmajid Ben Hamadou, MIRACL Laboratory, Institute of informatics and multimedia (ISIMS), Sfax University, Tunisia.

-  Yves Bestgen, Université Catholique de Louvain, Belgium.

-  Caroline Brown, XEROX, Grenoble, France.

-  Thierry Charnois, GRAYC, University of Caen, France.

-  Marc El-Beze , LIA, University of Avignon, France.

-  Michel Gagnon, École Polytechnique of Montréal, Montréal, Canada.

-  Michel generous, Centro Linguistica Computazionale da Universidade de Lisboa, Lisbon, Portugal.

-  Brigitte Grau, LIMSI, ENSIIE, Paris, France.

-  Nicolas Hernandez, LINA, University of Nantes, France.

-  Diana Inkpen, Ottawa University, Canada.

-  Leila Kosseim, Concordia University, Canada.

-  Cedric Lopez, VIDEO, Grenoble, France.

-  Stan Matwin, Dalhousie University, Canada.

-  Ruslan Mitkov, University of Wolverhampton, Great Britain.

-  Iadh Ounis, University of Glasgow, School of Computing Science, Great Britain.

-  Violaine Prince, LIRMM, Montpellier 2 University, France.

-  Horacio Saggion, Universidad Pompeu Fabra, Spain.

-  Jacques Savoy, University of Neuchatel, Switzerland.

-  Laurianne Sitbon, Queensland University of Technology, Australia.

-  Yannick Toussaint, INRIA, LORIA, Nancy, France.

-  Haifa Zargayouna, LIPN, Paris-Nord University, France.


TAL (Traitement Automatique des Langues) is an international journal that has been published by ATALA (Association pour le Traitement Automatique des Langues) for the past 40 years with the support of the CNRS. Over the past few years, it became an online journal, with possibility of ordering the paper versions. This does not, in any way, affect the selection and review process.


The articles (25 pages, PDF format) must be uploaded on the platform Style sheets are available on the web site of the journal ( The journal only publishes original contributions, in French or in English. Submissions in English will be accepted only from non-francophone authors.

Date de dernière mise à jour : 20 juillet 2013, auteur : Rédacteurs en chef.