Formalisation semi-automatique d'un vocabulaire patient/médecin dédié au cancer du sein

Abstract : Nowadays, social media is increasingly used by patients and health professionals. Most often, the patients are lay in the medical field, they use slang, abbreviations, and their own vocabulary during their exchanges. In order to automatically analyze texts from social networks , we need a specific vocabulary. Considering a corpus of documents from messages from social media like forums and Facebook, we describe the construction of a lexical resource that aligns the vocabulary of patients to that of health professionals. In order to build this resource and transform it into a SKOS ontology, we use several methods taking into account the linguistic and statistical aspects proposed in the literature. On the one hand, this work will improve information retrieval in health forums and on the other hand it will facilitate the development of statistical studies based on information extracted from these forums.
Document type :
Journal articles
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download
Contributor : Mike Donald Tapi Nzali <>
Submitted on : Wednesday, July 3, 2019 - 3:49:34 PM
Last modification on : Friday, July 19, 2019 - 10:16:48 AM


Explicit agreement for this submission





Mike Donald Tapi Nzali, Jérôme Azé, Sandra Bringay, Christian Lavergne, Caroline Mollevi, et al.. Formalisation semi-automatique d'un vocabulaire patient/médecin dédié au cancer du sein. Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, Lavoisier, 2016, 30 (5), pp.533-556. ⟨10.3166/ria.30.533-556⟩. ⟨hal-01583190⟩



Record views


Files downloads