Nos partenaires

CNRS

Rechercher





Accueil du site > Français > Evénements > Séminaires

Séminaires

 

L’IRIT étant localisé sur plusieurs sites, ses séminaires sont organisés et ont lieu soit à l’Université Toulouse 3 Paul Sabatier (UT3), l’Université Toulouse 1 Capitole (UT1), l’INP-ENSEEIHT ou l’Université Toulouse 2 Jean Jaurès (UT2J).

 

A Test Collection for Research on Depression and Language Use

Fabio CRESTANI - Faculty of Informatics, University of Lugano (Suisse)

Lundi 7 Novembre 2016, 14h00 - 16h00
UT3 Paul Sabatier, IRIT, Auditorium J. Herbrand
Version PDF :

Résumé

Several studies in the literature have shown that the words people use are indicative of their psychological states. In particular, depression was found to be associated with distinctive linguistic patterns. In this talk, I will describe our first steps to try to identify as early as possible if the writer is developing a depressive state. I will detail the methodology we have adopted to build and make publicly available a test collection on depression and language use. The resulting corpus includes a series of textual interactions written by different subjects. The new collection not only encourages research on differences in language between depressed and non-depressed individuals, but also on the evolution of the language use of depressed individuals. I will also present the new CLEF lab that we will run next year on this topic (eRisk 2017), that includes a novel depression detection task and the proposal of effectiveness measure to systematically compare early detection algorithms and baseline results.



Bio : Fabio Crestani est titulaire d'un diplôme en statistiques de l'Université de Padoue (Italie) et d'une maîtrise et d'un doctorat en sciences informatiques de l'Université de Glasgow (Royaume-Uni). Ses principaux domaines de recherche sont la recherche d'information, la fouille de textes et les bibliothèques numériques. Il a co-édité 10 livres et publié plus de 160 publications dans ces domaines de recherche. Il a été rédacteur en chef de Information Processing and Management (Elsevier) jusqu'en 2015 et membre du comité de rédaction de plusieurs revues. Ses travaux sur les réseaux sociaux sont particulièrement en phase avec les recherches menées par plusieurs équipes de l'IRIT.

Abstract

Several studies in the literature have shown that the words people use are indicative of their psychological states. In particular, depression was found to be associated with distinctive linguistic patterns. In this talk, I will describe our first steps to try to identify as early as possible if the writer is developing a depressive state. I will detail the methodology we have adopted to build and make publicly available a test collection on depression and language use. The resulting corpus includes a series of textual interactions written by different subjects. The new collection not only encourages research on differences in language between depressed and non-depressed individuals, but also on the evolution of the language use of depressed individuals. I will also present the new CLEF lab that we will run next year on this topic (eRisk 2017), that includes a novel depression detection task and the proposal of effectiveness measure to systematically compare early detection algorithms and baseline results.

 

Retour