s'authentifier
rss feed
HAL : halshs-00464810, version 1

Fiche détaillée  Export this paper
Corpus Linguistics 2009, Liverpool : United Kingdom (2009)
RHECITAS: citation analysis of French humanities articles
Ludovic Tanguy 1, Fanny Lalleman 1, Claire François 2, Philippe Muller 3, Patrick Séguéla 4
(2009)

The RHECITAS project aims at the analysis of citations in French Humanities and Social Sciences articles using natural language processing techniques. It is based on a corpus of online articles, through the aid of natural language processing tools. The project is funded by TGE-ADONIS (CNRS, French National Research Centre). Although very little research, either theoretical and technical, has been made on such data (most approaches focusing on science publications written in English), we developed two different tools that can automatically a) identify the more important items in a list of references, based on a number of linguistic cues, and b) extract relevant terms associated to a reference. These results show a new angle on citation analysis, both from a linguistic point of view and for practical applications.
1 :  Cognition, Langues, Langage, Ergonomie (CLLE)
CNRS : UMR5263 – Université Michel de Montaigne - Bordeaux III – Université Toulouse le Mirail - Toulouse II – Ecole Pratique des Hautes Etudes
2 :  Institut de l'information scientifique et technique (INIST)
CNRS : UPS76
3 :  Institut de recherche en informatique de Toulouse (IRIT)
CNRS : UMR5505 – Université des Sciences Sociales - Toulouse I – Université Toulouse le Mirail - Toulouse II – Université Paul Sabatier - Toulouse III
4 :  Synapse Développement
Synapse Développement
Humanities and Social Sciences/Linguistics
citation analysis – bibliometrics – HSS – online publications
Liste des fichiers attachés à ce document : 
PDF
CL09-Tanguy-online-proceedings.pdf(169.7 KB)