Copyright 2018 - copyright UMR ESPACE-DEV - 2017

Soutenance de thèse - Valetina Beretta - mardi 30 octobre - 14h - IMT Alès

thesard

Valentina Beretta soutiendra sa thèse le mardi 30 octobre 2018 à l’Ecole Mines-Télécom d’Alès à partir de 14h.
Titre : "Data veracity assessment: enhancing Truth Discovery using a priori knowledge" sous la direction conjointe de Sylvie Ranwez et de Sébastien Harispe (IMT Mines Alès) et d'Isabelle Mougenot (UMR ESPACE-DEV)
Jury  :
  • Catherine FARON ZUCKER, Maître de Conférences (HDR), Université de Nice Sophia Antipolis (Rapporteur)
  • Ollivier HAEMMERLÉ, Professeur, Université Toulouse (Rapporteur) 
  • Laure BERTI-EQUILLE, Directrice de Recherche, UMR 228 Espace Dev, IRD (Examinatrice)
  • Aldo GANGEMI, Professeur,  Université Paris13 / Institute of Cognitive Sciences and Technologies – CNR, Rome, Italie (Examinateur)
  • Jérôme DAVID, Maître de Conférences,  LIG, Université Grenoble Rhône-Alpes (Examinateur)
  • Sylvie RANWEZ, Professeur, LGI2P, IMT Mines Ales (Co-direction de thèse)
  • Isabelle MOUGENOT, Maître de Conférences (HDR), Université de Montpellier, UMR 228 Espace Dev (Co-direction de thèse) 
  • Sébastien HARISPE, Maître Assistant, LGI2P, IMT Mines Ales, (Encadrant de proximité)

Résumé de thèse
The notion of data veracity is increasingly getting attention due to the problem of misinformation and fake news. With more and more published online information it is becoming essential to develop models that automatically evaluate information veracity. Indeed, the task of evaluating data veracity is very difficult for humans. They are affected by confirmation bias that prevents them to objectively evaluate the information reliability. Moreover, the amount of information that is available nowadays makes this task time-consuming. The computational power of computer is required. It is critical to develop methods that are able to automatize this task.
In this thesis we focus on Truth Discovery models. These approaches address the data veracity problem when conflicting values about the same properties of real-world entities are provided by multiple sources. They aim to identify which are the true claims among the set of conflicting ones. More precisely, they are unsupervised models that are based on the rationale stating that true information is provided by reliable sources and reliable sources provide true information. The main contribution of this thesis consists in improving Truth Discovery models considering a priori knowledge expressed in ontologies. This knowledge may facilitate the identification of true claims. Two particular aspects of ontologies are considered. First of all, we explore the semantic dependencies that may exist among different values, i.e. the ordering of values through certain conceptual relationships. Indeed, two different values are not necessary conflicting. They may represent the same concept, but with different levels of detail. In order to integrate this kind of knowledge into existing approaches, we use the mathematical models of partial order. Then, we consider recurrent patterns that can be derived from ontologies. This additional information indeed reinforces the confidence in certain values when certain recurrent patterns are observed. In this case, we model recurrent patterns using rules. Experiments that were conducted both on synthetic and real-world datasets show that a priori knowledge enhances existing models and paves the way towards a more reliable information world. Source code as well as synthetic and real-world datasets are freely available.
Lieu
IMT Mines d’Alès
6 avenue de Clavières
30100 Alès
f t g m

Connexion intranet

Connexion

Connexion à votre compte

Identifiant
Mot de passe
Maintenir la connexion active sur ce site
UMR ESPACE-DEV
France : Maison de la télédétection - 500 rue JF Breton - 34093 Montpellier cedex 5
Tél : 04 67 55 86 05 - Fax : 04 67 54 87 00
Guyane : IRD - 0.275 Km Route de Montabo - BP 165 - 97323 Cayenne cedex
Nouvelle-Calédonie : Centre IRD Anse Vata - BPA5 98848 Nouméa Cedex
Réunion : Université de la Réunion
15 avenue René Cassin - BP 7151 - 97715 Saint-Denis Messag cedex 9