Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A corpus of debunked and verified user-generated videos

A corpus of debunked and verified user-generated videos As user-generated content (UGC) is entering the news cycle alongside content captured by news professionals, it is important to detect misleading content as early as possible and avoid disseminating it. The purpose of this paper is to present an annotated dataset of 380 user-generated videos (UGVs), 200 debunked and 180 verified, along with 5,195 near-duplicate reposted versions of them, and a set of automatic verification experiments aimed to serve as a baseline for future comparisons.Design/methodology/approachThe dataset was formed using a systematic process combining text search and near-duplicate video retrieval, followed by manual annotation using a set of journalism-inspired guidelines. Following the formation of the dataset, the automatic verification step was carried out using machine learning over a set of well-established features.FindingsAnalysis of the dataset shows distinctive patterns in the spread of verified vs debunked videos, and the application of state-of-the-art machine learning models shows that the dataset poses a particularly challenging problem to automatic methods.Research limitations/implicationsPractical limitations constrained the current collection to three platforms: YouTube, Facebook and Twitter. Furthermore, there exists a wealth of information that can be drawn from the dataset analysis, which goes beyond the constraints of a single paper. Extension to other platforms and further analysis will be the object of subsequent research.Practical implicationsThe dataset analysis indicates directions for future automatic video verification algorithms, and the dataset itself provides a challenging benchmark.Social implicationsHaving a carefully collected and labelled dataset of debunked and verified videos is an important resource both for developing effective disinformation-countering tools and for supporting media literacy activities.Originality/valueBesides its importance as a unique benchmark for research in automatic verification, the analysis also allows a glimpse into the dissemination patterns of UGC, and possible telltale differences between fake and real content. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Online Information Review Emerald Publishing

A corpus of debunked and verified user-generated videos

Download PDF
17 pages

Loading next page...
 
/lp/emerald-publishing/a-corpus-of-debunked-and-verified-user-generated-videos-kvY1eXqwSF
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1468-4527
DOI
10.1108/oir-03-2018-0101
Publisher site
See Article on Publisher Site

Abstract

As user-generated content (UGC) is entering the news cycle alongside content captured by news professionals, it is important to detect misleading content as early as possible and avoid disseminating it. The purpose of this paper is to present an annotated dataset of 380 user-generated videos (UGVs), 200 debunked and 180 verified, along with 5,195 near-duplicate reposted versions of them, and a set of automatic verification experiments aimed to serve as a baseline for future comparisons.Design/methodology/approachThe dataset was formed using a systematic process combining text search and near-duplicate video retrieval, followed by manual annotation using a set of journalism-inspired guidelines. Following the formation of the dataset, the automatic verification step was carried out using machine learning over a set of well-established features.FindingsAnalysis of the dataset shows distinctive patterns in the spread of verified vs debunked videos, and the application of state-of-the-art machine learning models shows that the dataset poses a particularly challenging problem to automatic methods.Research limitations/implicationsPractical limitations constrained the current collection to three platforms: YouTube, Facebook and Twitter. Furthermore, there exists a wealth of information that can be drawn from the dataset analysis, which goes beyond the constraints of a single paper. Extension to other platforms and further analysis will be the object of subsequent research.Practical implicationsThe dataset analysis indicates directions for future automatic video verification algorithms, and the dataset itself provides a challenging benchmark.Social implicationsHaving a carefully collected and labelled dataset of debunked and verified videos is an important resource both for developing effective disinformation-countering tools and for supporting media literacy activities.Originality/valueBesides its importance as a unique benchmark for research in automatic verification, the analysis also allows a glimpse into the dissemination patterns of UGC, and possible telltale differences between fake and real content.

Journal

Online Information Review – Emerald Publishing

Published: Feb 12, 2019

Keywords: Video verification; Fake news; Disinformation detection; User-generated content; Social media; Dataset

References

  • Detection and visualization of misleading content on Twitter
    Boididou, C.; Papadopoulos, S.; Zampoglou, M.; Apostolidis, L.; Papadopoulou, O.; Kompatsiaris, Y.
  • Verifying multimedia use at mediaeval 2015
    Boididou, C.; Andreadou, K.; Papadopoulos, S.; Dang-Nguyen, D.-T.; Boato, G.; Riegler, M.; Kompatsiaris, Y.
  • Verifying multimedia use at mediaeval 2016
    Boididou, C.; Papadopoulos, S.; Dang-Nguyen, D.-T.; Boato, G.; Riegler, M.; Middleton, S.E.; Petlund, A.; Kompatsiaris, Y.
  • Fragile watermarking using Karhunen–Loève transform: the KLT-F approach
    Botta, M.; Cavagnino, D.; Pomponiu, V.
  • Information credibility on twitter
    Castillo, C.; Mendoza, M.; Poblete, B.
  • A computer readability formula designed for machine scoring
    Coleman, M.; Liau, T.L.
  • An effective SVD-based image tampering detection and self-recovery using active watermarking
    Dadkhah, S.; Manaf, A.A.; Hori, Y.; Hassanien, A.E.; Sadeghi, S.
  • Behavior knowledge space-based fusion for copy–move forgery detection
    Ferreira, A.; Felipussi, S.C.; Alfaro, C.; Fonseca, P.; Vargas-Munoz, J.E.; dos Santos, J.A.; Rocha, A.
  • Faking sandy: characterizing and identifying fake images on twitter during hurricane sandy
    Gupta, A.; Lamba, H.; Kumaraguru, P.; Joshi, A.
  • The quest to automate fact-checking
    Hassan, N.; Adair, B.; Hamilton, J.; Li, C.; Tremayne, M.; Yang, J.; Yu, C.
  • A clash of cultures: the integration of user-generated content within professional journalistic frameworks at British newspaper websites
    Hermida, A.; Thurman, N.
  • Near-duplicate video retrieval with deep metric learning
    Kordopatis-Zilos, G.; Papadopoulos, S.; Patras, I.; Kompatsiaris, Y.
  • False information on web and social media: a survey
    Kumar, S.; Shah, N.
  • Web video verification using contextual cues
    Papadopoulou, O.; Zampoglou, M.; Papadopoulos, S.; Kompatsiaris, Y.
  • The InVID plug-in: web video verification on the browser
    Teyssou, D.; Leung, J.-M.; Apostolidis, E.; Apostolidis, K.; Papadopoulos, S.; Zampoglou, M.; Papadopoulou, O.; Mezaris, V.
  • Rumor gauge: predicting the veracity of rumors on twitter
    Vosoughi, S.; Mohsenvand, M.N.; Roy, D.
  • False rumors detection on Sina Weibo by propagation structures
    Wu, K.; Yang, S.; Zhu, K.Q.
  • Visual memes in social media: tracking real-world news in YouTube videos
    Xie, L.; Natsev, A.; Kender, J.R.; Hill, M.; Smith, J.R.
  • Large-scale evaluation of splicing localization algorithms for web images
    Zampoglou, M.; Papadopoulos, S.; Kompatsiaris, Y.
  • Iterative copy-move forgery detection based on a new interest point detector
    Zandi, M.; Mahmoudi-Aznaveh, A.; Talebpour, A.
  • Detection and resolution of rumours in social media: a survey
    Zubiaga, A.; Aker, A.; Bontcheva, K.; Liakata, M.; Procter, R.
  • Rumor has it: identifying misinformation in microblogs
    Qazvinian, V.; Rosengren, E.; Radev, D.R.; Mei, Q.