1. User profile detection in health online fora
- Author
-
Pertin, Camille, Deccache, Carole, Gagnayre, Rémi, Hamon, Thierry, Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI), Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919), Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11), Laboratoire Educations et Pratiques de Santé (LEPS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Sorbonne Paris Cité (USPC)-Université Paris 13 (UP13), Clinique du Château de Verhnes, Université Paris 13 (UP13), Adrien Ugon, Daniel Karlsson, Gunnar O. Klein, Anne Moen, Adrien Ugon, Daniel Karlsson, Gunnar O. Klein, Anne Moen, and Publications, Limsi
- Subjects
Machine Learning ,[INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL] ,Demographic Information ,Online Discussion Fora ,[INFO]Computer Science [cs] ,[INFO] Computer Science [cs] ,[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] ,Natural Language Processing - Abstract
International audience; Exchanges between diabetic patients on discussion fora permit to study their understanding of their disorder, their behavior and needs when facing health problems. When analyzing these exchanges and behavior, it is necessary to collect information on user profile. We present an approach combining lexicon and supervised classifiers for the identification of age and gender of contributors, their disorders and relation between contributor and patient. According to parameters of the method, we obtain precision between 100% for gender and 53.48% for disorders.
- Published
- 2018