Multilingual Disinformation Detection for Digital Advertising - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Multilingual Disinformation Detection for Digital Advertising

Zofia Trstanova
  • Fonction : Auteur
Nadir El Manouzi
  • Fonction : Auteur
Maryline Chen
  • Fonction : Auteur
Andre L V da Cunha
  • Fonction : Auteur
Sergei Ivanov
  • Fonction : Auteur

Résumé

In today's world, the presence of online disinformation and propaganda is more widespread than ever. Independent publishers are funded mostly via digital advertising, which is unfortunately also the case for those publishing disinformation content. The question of how to remove such publishers from advertising inventory has long been ignored, despite the negative impact on the open internet. In this work, we make the first step towards quickly detecting and red-flagging websites that potentially manipulate the public with disinformation. We build a machine learning model based on multilingual text embeddings that first determines whether the page mentions a topic of interest, then estimates the likelihood of the content being malicious, creating a shortlist of publishers that will be reviewed by human experts. Our system empowers internal teams to proactively, rather than defensively, blacklist unsafe content, thus protecting the reputation of the advertisement provider.
Fichier principal
Vignette du fichier
ICML22_Workshop_PCA (1).pdf (382.53 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03731711 , version 1 (21-07-2022)

Identifiants

  • HAL Id : hal-03731711 , version 1

Citer

Zofia Trstanova, Nadir El Manouzi, Maryline Chen, Andre L V da Cunha, Sergei Ivanov. Multilingual Disinformation Detection for Digital Advertising. ICML 2022 : Disinformation Countermeasures and Machine Learning Workshop, Jul 2022, Baltimore, United States. ⟨hal-03731711⟩
40 Consultations
54 Téléchargements

Partager

Gmail Facebook X LinkedIn More