en
Doctoral thesis
English

Methods and tools to retrieve reliable Health Information on the Internet

Defense date2016-10-04
Abstract

The goal of the research activities conducted and presented in this thesis is to propose combined tools to improve access to quality health content online. The thesis presents the three pillars of retrieving quality health information: query formulation, readability and trust level. The research uses the quality criteria defined for health Web publishers and in use for the past 20 years in the HONcode certification process. This thesis first explores the automated detection of HONcode principles for health websites. It considers the feasibility of such an automated detection, the benchmarking and assessing of natural language processing methods. It then studies the use of HONcode principle classifiers that can be applied to health Web pages. Thirdly, it examines directions for the integration of the tools into search engines. And lastly, a usability testing evaluates the benefits of filtering capability of trusted sources via the automated tool developed within the research activities.

eng
Keywords
  • HONcode
  • Trustworthiness
  • Quality standards
  • Automated detection, classification
  • Health Internet
  • Machine learning
  • Named entity recognition
  • Natural language processing
  • HONcode
  • Fiabilité
  • Normes de qualité
  • Standard de qualité
  • Ethique
  • Détection automatisée
  • Classification
  • Santé Internet
  • Apprentissage automatique
  • Reconnaissance d'entités nommées
  • Traitement du langage naturel
Citation (ISO format)
BOYER WALTHER, Célia. Methods and tools to retrieve reliable Health Information on the Internet. 2016. doi: 10.13097/archive-ouverte/unige:88907
Main files (1)
Thesis
accessLevelRestricted
Identifiers
758views
17downloads

Technical informations

Creation10/10/2016 2:33:00 PM
First validation10/10/2016 2:33:00 PM
Update time03/15/2023 12:55:31 AM
Status update03/15/2023 12:55:31 AM
Last indexation09/18/2023 8:51:48 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack