Skip to Main content Skip to Navigation

Détection automatique de l'ironie dans les contenus générés par les utilisateurs

Jihen Karoui 1 
1 IRIT-MELODI - MEthodes et ingénierie des Langues, des Ontologies et du DIscours
IRIT - Institut de recherche en informatique de Toulouse
Abstract : This thesis aims to detect figurative language devices in social networks. We focus in particular on irony and sarcasm in Twitter and propose an approach based on supervised learning to predict if a tweet is ironic or not. This required three steps: (1) Analyze the pragmatic phenomena of irony and a multi-level annotation of a corpus of reference, (2) Development of an automatic detection system for French tweets that exploits both semantic features and the extra-linguistic context, (3) Study of the portability of the model to detect irony in a multilingual setting  (Italian, English and Arabic). The obtained results for this extremely complex task are very encouraging and will allow a significant improvement of polarity detection in sentiments analysis.
Complete list of metadata

Cited literature [161 references]  Display  Hide  Download
Contributor : Jihen KAROUI Connect in order to contact the contributor
Submitted on : Thursday, October 12, 2017 - 5:36:37 PM
Last modification on : Monday, July 4, 2022 - 10:07:58 AM


Détection automatique de l'ir...
Files produced by the author(s)


  • HAL Id : tel-01615868, version 1


Jihen Karoui. Détection automatique de l'ironie dans les contenus générés par les utilisateurs. Intelligence artificielle [cs.AI]. Université de Toulouse 3 Paul Sabatier; Faculté des Sciences Economiques et de Gestion, Université de Sfax (Tunisie), 2017. Français. ⟨tel-01615868⟩



Record views


Files downloads