Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Presentation of the InVID tool for social media verification


Published on

Presentation of the InVID tool for social media verification through contextual analysis, at the Media Informatics Lab meeting on detection and verification of socially shared videos.

Published in: Technology
  • Be the first to comment

  • Be the first to like this

Presentation of the InVID tool for social media verification

  1. 1. Towards Automatic Detection of Misinformation in Social Media Symeon (Akis) Papadopoulos - @sympap Information Technologies Institute (ITI) / Centre for Research and Technology Hellas (CERTH) Workshop on Tools for Video Discovery & Verification in Social Media Dec 14, 2017 @ Thessaloniki, Greece
  2. 2. Real or fake?
  3. 3. Real or fake?
  4. 4. Real or fake?
  5. 5. Real or fake?
  6. 6. Types of misinformation
  7. 7. Towards computational verification
  8. 8. The Tweet Verification Assistant A web-based service for marking an input tweet as “real” or “fake” 2012 first ideas and experiments (SocialSensor) 2013-2016 main research, development and validation (REVEAL) 2016-now incremental refinements and testing (InVID)
  9. 9. User interface
  10. 10. Credibility cues (aka features)
  11. 11. Building the classification model
  12. 12. Tweet Verification Corpus • 53 events or hoaxes involving false and/or real imagery and videos • 257 cases of “fake” content, 261 of “real” • 10,634 tweets sharing “fake” content, 7,223 tweets sharing “real” content • Examples events: • Hurricane Sandy • Boston Marathon bombing • Sochi Olympics • MA Flight 370 • Nepal Earthquake…
  13. 13. The “Verifying Multimedia Use” Task •VMU: Organized in 2015 and 2016 as part of the MediaEval benchmarking initiative •Goal: compare automated approaches for fake tweet detection •Outcomes: several methods from different research groups across the globe were tested and compared
  14. 14. Experimental validation 92.5% accuracy in identifying misleading posts 88-98% accuracy depending on language (major languages tested: en, fr, es, nl) New features, bagging and agreement-based retraining led to significant improvements! One of the top performing methods in the VMU 2015 & 2016 tasks!
  15. 15. Context Analysis and Aggregation • Available at: • YouTube, Facebook and Twitter videos • metadata from APIs • mentioned locations • “verification”-related comments • thumbnails for near-duplicate search • weather at time and location of video • video sharing on Twitter
  16. 16. Tip in comment led to debunking A comment points to second 23 of the video where suddenly the snake appears out of nowhere
  17. 17. # verification comments too high 1550 verification-related comments out of 4219 total number of comments
  18. 18. Tweets sharing video are flagged 37 out of 43 tweets sharing the video are classified as fake
  19. 19. Video verification experiments • 117 fake videos and 110 real videos • The dataset covers different types of manipulation: • staged videos, • videos misrepresenting the depicted event, • videos of past events claimed to be captured now, • digitally manipulated videos. • A supervised learning approach using credibility features extracted from video comments and video metadata managed to achieve promising accuracy: P=72%, R=86%, F=79%
  20. 20. Limitations • Models are still based on aged training data (could be affected by concept drift…) • Results not always easy to justify or explain to end users • A well-informed adversary can easily fool the model by emulating “credible-looking” posts • Journalists are still expected to make the final decision!
  21. 21. The future of misinformation
  22. 22. Acknowledgements • Christina Boididou (Feature extraction, model building, initial REST API development) • Olga Papadopoulou (Validation, code refactoring, REST API refinement and support) • Lazaros Apostolidis (UI/UX) • Markos Zampoglou (Evaluation) • Yiannis Kompatsiaris (PI)
  23. 23. Thank you! Get in touch! Akis Papadopoulos / @sympap
  24. 24. References • Boididou, C., Papadopoulos, S., Kompatsiaris, Y., Schifferes, S., & Newman, N. (2014, April). Challenges of computational verification in social multimedia. In Proceedings of the 23rd International Conference on World Wide Web (pp. 743-748). ACM • Boididou, C., Middleton, S. E., Jin, Z., Papadopoulos, S., Dang-Nguyen, D. T., Boato, G., & Kompatsiaris, Y. (2017). Verifying information with multimedia content on twitter. Multimedia Tools and Applications, 1-27 • Boididou, C., Papadopoulos, S., Apostolidis, L., & Kompatsiaris, Y. (2017, June). Learning to Detect Misleading Content on Twitter. In Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval (pp. 278-286). ACM • Castillo, C., Mendoza, M., & Poblete, B. (2011, March). Information credibility on twitter. In Proceedings of the 20th international conference on World Wide Web (pp. 675-684). ACM • Liu, M. Y., Breuel, T., & Kautz, J. (2017). Unsupervised Image-to-Image Translation Networks. arXiv preprint arXiv:1703.00848 • Papadopoulou, O., Zampoglou, M., Papadopoulos, S., & Kompatsiaris, Y. (2017, June). Web Video Verification using Contextual Cues. In Proceedings of the 2nd International Workshop on Multimedia Forensics and Security (pp. 6-10). ACM • Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint arXiv:1703.10593.