Why am I reading this? Explaining Personalized News Recommender Systems

S. Arnórsson; F. Abeillon; I. Al-Hazwani; J. Bernard; H. Hauptmann; M. El-Assady

doi:10.2312/eurova.20231099

Why am I reading this? Explaining Personalized News Recommender Systems

S. Arnórsson
, F. Abeillon
, I. Al-Hazwani
, J. Bernard
, H. Hauptmann
, M. El-Assady

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Social media and online platforms significantly impact what millions of people get exposed to daily, mainly through recommended content. Hence, recommendation processes have to benefit individuals and society. With this in mind, we present the visual workspace NewsRecXplain, with the goals of (1) explaining and raising awareness about recommender systems, (2) enabling individuals to control and customize news recommendations, and (3) empowering users to contextualize their news recommendations to escape from their filter bubbles. This visual workspace achieves these goals by allowing users to configure their own individualized recommender system, whose news recommendations can then be explained within the workspace by way of embeddings and statistics on content diversity.

Original language	English
Title of host publication	International Workshop on Visual Analytics
Subtitle of host publication	EuroVA2023
Publisher	Eurographics Association
ISBN (Print)	9783038682226
DOIs	https://doi.org/10.2312/eurova.20231099
Publication status	Published - 2023

Access to Document

10.2312/eurova.20231099Licence: CC BY

067-072Final published version, 3.86 MBLicence: CC BY

Cite this

@inproceedings{eb97a36facc248b780146494c764953a,

title = "Why am I reading this? Explaining Personalized News Recommender Systems",

abstract = "Social media and online platforms significantly impact what millions of people get exposed to daily, mainly through recommended content. Hence, recommendation processes have to benefit individuals and society. With this in mind, we present the visual workspace NewsRecXplain, with the goals of (1) explaining and raising awareness about recommender systems, (2) enabling individuals to control and customize news recommendations, and (3) empowering users to contextualize their news recommendations to escape from their filter bubbles. This visual workspace achieves these goals by allowing users to configure their own individualized recommender system, whose news recommendations can then be explained within the workspace by way of embeddings and statistics on content diversity.",

author = "S. Arn{\'o}rsson and F. Abeillon and I. Al-Hazwani and J. Bernard and H. Hauptmann and M. El-Assady",

year = "2023",

doi = "10.2312/eurova.20231099",

language = "English",

isbn = "9783038682226",

booktitle = "International Workshop on Visual Analytics",

publisher = "Eurographics Association",

}

TY - GEN

T1 - Why am I reading this? Explaining Personalized News Recommender Systems

AU - Arnórsson, S.

AU - Abeillon, F.

AU - Al-Hazwani, I.

AU - Bernard, J.

AU - Hauptmann, H.

AU - El-Assady, M.

PY - 2023

Y1 - 2023

N2 - Social media and online platforms significantly impact what millions of people get exposed to daily, mainly through recommended content. Hence, recommendation processes have to benefit individuals and society. With this in mind, we present the visual workspace NewsRecXplain, with the goals of (1) explaining and raising awareness about recommender systems, (2) enabling individuals to control and customize news recommendations, and (3) empowering users to contextualize their news recommendations to escape from their filter bubbles. This visual workspace achieves these goals by allowing users to configure their own individualized recommender system, whose news recommendations can then be explained within the workspace by way of embeddings and statistics on content diversity.

AB - Social media and online platforms significantly impact what millions of people get exposed to daily, mainly through recommended content. Hence, recommendation processes have to benefit individuals and society. With this in mind, we present the visual workspace NewsRecXplain, with the goals of (1) explaining and raising awareness about recommender systems, (2) enabling individuals to control and customize news recommendations, and (3) empowering users to contextualize their news recommendations to escape from their filter bubbles. This visual workspace achieves these goals by allowing users to configure their own individualized recommender system, whose news recommendations can then be explained within the workspace by way of embeddings and statistics on content diversity.

UR - https://www.scopus.com/pages/publications/85170542014

U2 - 10.2312/eurova.20231099

DO - 10.2312/eurova.20231099

M3 - Conference contribution

SN - 9783038682226

BT - International Workshop on Visual Analytics

PB - Eurographics Association

ER -

Why am I reading this? Explaining Personalized News Recommender Systems

Abstract

Access to Document

Other files and links

Fingerprint

Cite this