ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Are Current Filter Bubble Metrics Coherent?

Maxwell-Lawford, Victoria
(2023)

Files

MAXWELL-LAWFORD_78312000_2023.pdf
  • UCLouvain restricted access
  • Adobe PDF
  • 774.38 KB

Details

Supervisors
Corentin Vande Kerckhove
Faculty
Louvain School of Management
Degree label
Master [60] en sciences de gestion
Abstract
On the Internet, people are facing the problem of abundance of information. To solve this issue, recommendation systems came about. By suggesting content that is most likely to interest the user, other opinions are left aside, leaving the user blindsided from other points of view and trapping him or her in a so-called Filter Bubble. The phenomenon is not accepted across the whole academic field. Many do not agree on a common definition. This paper aims to implement the different metrics that have been put forward and show the presence of Filter bubbles in news recommendations. The metrics' results indicate different status regarding the filter bubble for one same individual. There is incoherence among the metrics. They do not capture the diversity of online content in the same way. Making it impossible to say for certain whether a user is in a Filter bubble or not. Thus, making it harder to confirm the existence of the Filter bubble in news websites.