FakeClaim: A Multiple Platform-driven Dataset for Identification of Fake News on 2023 Israel-Hamas War

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shahi, Gautam Kishore, Jaiswal, Amit Kumar, Mandl, Thomas
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913215196168192
author Shahi, Gautam Kishore
Jaiswal, Amit Kumar
Mandl, Thomas
author_facet Shahi, Gautam Kishore
Jaiswal, Amit Kumar
Mandl, Thomas
contents We contribute the first publicly available dataset of factual claims from different platforms and fake YouTube videos on the 2023 Israel-Hamas war for automatic fake YouTube video classification. The FakeClaim data is collected from 60 fact-checking organizations in 30 languages and enriched with metadata from the fact-checking organizations curated by trained journalists specialized in fact-checking. Further, we classify fake videos within the subset of YouTube videos using textual information and user comments. We used a pre-trained model to classify each video with different feature combinations. Our best-performing fine-tuned language model, Universal Sentence Encoder (USE), achieves a Macro F1 of 87\%, which shows that the trained model can be helpful for debunking fake videos using the comments from the user discussion. The dataset is available on Github\footnote{https://github.com/Gautamshahi/FakeClaim}
format Preprint
id arxiv_https___arxiv_org_abs_2401_16625
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FakeClaim: A Multiple Platform-driven Dataset for Identification of Fake News on 2023 Israel-Hamas War
Shahi, Gautam Kishore
Jaiswal, Amit Kumar
Mandl, Thomas
Information Retrieval
Social and Information Networks
We contribute the first publicly available dataset of factual claims from different platforms and fake YouTube videos on the 2023 Israel-Hamas war for automatic fake YouTube video classification. The FakeClaim data is collected from 60 fact-checking organizations in 30 languages and enriched with metadata from the fact-checking organizations curated by trained journalists specialized in fact-checking. Further, we classify fake videos within the subset of YouTube videos using textual information and user comments. We used a pre-trained model to classify each video with different feature combinations. Our best-performing fine-tuned language model, Universal Sentence Encoder (USE), achieves a Macro F1 of 87\%, which shows that the trained model can be helpful for debunking fake videos using the comments from the user discussion. The dataset is available on Github\footnote{https://github.com/Gautamshahi/FakeClaim}
title FakeClaim: A Multiple Platform-driven Dataset for Identification of Fake News on 2023 Israel-Hamas War
topic Information Retrieval
Social and Information Networks
url https://arxiv.org/abs/2401.16625