Skip to main content
SpringerLink
Log in

Exploring the Role of Visual Content in Fake News Detection

  • Chapter
  • First Online:
Book cover Disinformation, Misinformation, and Fake News in Social Media

Part of the book series: Lecture Notes in Social Networks ((LNSN))

Abstract

The increasing popularity of social media promotes the proliferation of fake news, which has caused significant negative societal effects. Therefore, fake news detection on social media has recently become an emerging research area of great concern. With the development of multimedia technology, fake news attempts to utilize multimedia content with images or videos to attract and mislead consumers for rapid dissemination, which makes visual content an important part of fake news. Despite the importance of visual content, our understanding about the role of visual content in fake news detection is still limited. This chapter presents a comprehensive review of the visual content in fake news, including the basic concepts, effective visual features, representative detection methods and challenging issues of multimedia fake news detection. This chapter can help readers to understand the role of visual content in fake news detection, and effectively utilize visual content to assist in detecting multimedia fake news.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 199.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://twitter.com/

  2. 2.

    https://weibo.com/

  3. 3.

    http://www.cac.gov.cn/2019-08/30/c_1124938750.htm

  4. 4.

    https://www.journalism.org/2018/09/10/news-use-across-social-media-platforms-2018/

  5. 5.

    https://www.telegraph.co.uk/finance/markets/10013768/Bogus-AP-tweet-about-explosion-at-the-White-House-wipes-billions-off-US-markets.html

  6. 6.

    https://www.washingtonpost.com/world/asia_pacific/as-mob-lynchings-fueled-by-whatsapp-sweep-india-authorities-struggle-to-combat-fake-news/2018/07/02/683a1578-7bba-11e8-ac4e-421ef7165923_story.html

  7. 7.

    https://www.invid-project.eu/tools-and-services/invid-verification-plugin/

  8. 8.

    https://www.businesswire.com/news/home/20190204005613/en/Visual-SearchWins-Text-Consumers%E2%80%99-Trusted-Information

  9. 9.

    https://www.wired.com/2016/12/photos-fuel-spread-fake-news/

  10. 10.

    https://images.google.com/

  11. 11.

    http://mediabiasfactcheck.com/

  12. 12.

    https://github.com/MKLab-ITI/image-verification-corpus

  13. 13.

    https://github.com/KaiDMML/FakeNewsNet

  14. 14.

    https://www.politifact.com/

  15. 15.

    https://www.gossipcop.com/

  16. 16.

    http://mcg.ict.ac.cn/wordpress/share/mcg-fnews/

  17. 17.

    https://service.account.weibo.com/

  18. 18.

    https://www.newsverify.com/

  19. 19.

    http://gitlab.com/didizlatkova/fake-image-detection

  20. 20.

    https://www.snopes.com/fact-check/category/photos/

  21. 21.

    https://image.baidu.com/

  22. 22.

    http://www.fotoforensics.com/

  23. 23.

    http://reveal-mklab.iti.gr/reveal/

  24. 24.

    https://www.invid-project.eu/tools-and-services/invid-verification-plugin/

  25. 25.

    https://www.biendata.com/competition/falsenews/

References

  1. Allcott, H., Gentzkow, M.: Social media and fake news in the 2016 election. J. Econ. Perspect. 31(2), 211–236 (2017)

    Article  Google Scholar 

  2. Bianchi, T., Piva, A.: Image forgery localization via block-grained analysis of jpeg artifacts. IEEE Trans. Inf. Forensic. Secur. 7(3), 1003–1017 (2012)

    Article  Google Scholar 

  3. Boididou, C., Andreadou, K., Papadopoulos, S., Dang-Nguyen, D.T., Boato, G., Riegler, M., Kompatsiaris, Y., et al.: Verifying multimedia use at mediaeval 2015. In: MediaEval (2015)

    Google Scholar 

  4. Boididou, C., Papadopoulos, S., Dang-Nguyen, D.T., Boato, G., Kompatsiaris, Y.: The certh-unitn participation@ verifying multimedia use 2015. In: MediaEval (2015)

    Google Scholar 

  5. Boididou, C., Papadopoulos, S., Dang-Nguyen, D.T., Boato, G., Riegler, M., Middleton, S.E., Petlund, A., Kompatsiaris, Y., et al.: Verifying multimedia use at mediaeval 2016. In: MediaEval (2016)

    Google Scholar 

  6. Boididou, C., Papadopoulos, S., Zampoglou, M., Apostolidis, L., Papadopoulou, O., Kompatsiaris, Y.: Detection and visualization of misleading content on twitter. Int. J. Multimed. Inf. Retr. 7(1), 71–86 (2018)

    Article  Google Scholar 

  7. Brandtzaeg, P.B., Lüders, M., Spangenberg, J., Rath-Wiggins, L., Følstad, A.: Emerging journalistic verification practices concerning social media. Journal. Pract. 10(3), 323–342 (2016)

    Google Scholar 

  8. Cao, J., Sheng, Q., Qi, P., Zhong, L., Wang, Y., Zhang, X.: False news detection on social media. arXiv preprint arXiv:1908.10818 (2019)

    Google Scholar 

  9. Dhruv, K., Jaipal Singh, G., Manish, G., Vasudeva, V.: Mvae: multimodal variational autoencoder for fake news detection. In: Proceedings of the 2019 World Wide Web Conference. ACM (2019)

    Google Scholar 

  10. Ferrara, P., Bianchi, T., De Rosa, A., Piva, A.: Image forgery localization via fine-grained analysis of cfa artifacts. IEEE Trans. Inf. Forensic. Secur. 7(5), 1566–1577 (2012)

    Article  Google Scholar 

  11. Goljan, M., Fridrich, J., Chen, M.: Defending against fingerprint-copy attack in sensor-based camera identification. IEEE Trans. Inf. Forensic. Secur. 6(1), 227–236 (2010)

    Article  Google Scholar 

  12. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)

    Google Scholar 

  13. Jaiswal, A., Sabir, E., AbdAlmageed, W., Natarajan, P.: Multimedia semantic integrity assessment using joint embedding of images and text. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 1465–1471. ACM (2017)

    Google Scholar 

  14. Jaiswal, A., Wu, Y., AbdAlmageed, W., Masi, I., Natarajan, P.: Aird: adversarial learning framework for image repurposing detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11330–11339 (2019)

    Google Scholar 

  15. Jin, Z., Cao, J., Guo, H., Zhang, Y., Luo, J.: Multimodal fusion with recurrent neural networks for rumor detection on microblogs. In: Proceedings of the 2017 ACM on Multimedia Conference, pp. 795–816. ACM (2017)

    Google Scholar 

  16. Jin, Z., Cao, J., Luo, J., Zhang, Y.: Image credibility analysis with effective domain transferred deep networks. arXiv preprint arXiv:1611.05328 (2016)

    Google Scholar 

  17. Jin, Z., Cao, J., Zhang, Y., Zhou, J., Tian, Q.: Novel visual and statistical image features for microblogs news verification. IEEE Trans. Multimed. 19(3), 598–608 (2017)

    Article  Google Scholar 

  18. Kumar, S., Shah, N.: False information on web and social media: a survey. arXiv preprint arXiv:1804.08559 (2018)

    Google Scholar 

  19. Lang, P.J.: A bio-informational theory of emotional imagery. Psychophysiology 16(6), 495–512 (1979)

    Article  Google Scholar 

  20. Lazer, D.M., Baum, M.A., Benkler, Y., Berinsky, A.J., Greenhill, K.M., Menczer, F., Metzger, M.J., Nyhan, B., Pennycook, G., Rothschild, D., et al.: The science of fake news. Science 359(6380), 1094–1096 (2018)

    Article  Google Scholar 

  21. Li, W., Yuan, Y., Yu, N.: Passive detection of doctored jpeg image via block artifact grid extraction. Signal Process. 89(9), 1821–1829 (2009)

    Article  Google Scholar 

  22. Li, Y., Chang, M.C., Lyu, S.: In Ictu Oculi: exposing ai generated fake face videos by detecting eye blinking. arXiv preprint arXiv:1806.02877 (2018)

    Google Scholar 

  23. Li, Y., Lyu, S.: Exposing deepfake videos by detecting face warping artifacts. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 46–52 (2019)

    Google Scholar 

  24. Luo, W., Wu, M., Huang, J.: Mpeg recompression detection based on block artifacts. In: Security, Forensics, Steganography, and Watermarking of Multimedia Contents X, vol. 6819, p 68190X. International Society for Optics and Photonics (2008)

    Google Scholar 

  25. Ma, J., Gao, W., Mitra, P., Kwon, S., Jansen, B.J., Wong, K.F., Cha, M.: Detecting rumors from microblogs with recurrent neural networks. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pp. 3818–3824. AAAI Press (2016)

    Google Scholar 

  26. Mahdian, B., Saic, S.: Using noise inconsistencies for blind image forensics. Image Vision Comput. 27(10), 1497–1503 (2009)

    Article  Google Scholar 

  27. McCloskey, S., Albright, M.: Detecting GAN-generated imagery using color cues. arXiv preprint arXiv:1812.08247 (2018)

    Google Scholar 

  28. Muhammad, G., Al-Hammadi, M.H., Hussain, M., Bebis, G.: Image forgery detection using steerable pyramid transform and local binary pattern. Mach. Vis. Appl. 25(4), 985–995 (2014)

    Article  Google Scholar 

  29. Nataraj, L., Mohammed, T.M., Manjunath, B., Chandrasekaran, S., Flenner, A., Bappy, J.H., Roy-Chowdhury, A.K.: Detecting GAN generated fake images using co-occurrence matrices. arXiv preprint arXiv:1903.06836 (2019)

    Google Scholar 

  30. Qi, P., Cao, J., Yang, T., Guo, J., Li, J.: Exploiting multi-domain visual information for fake news detection. In: 19th IEEE International Conference on Data Mining. IEEE (2019)

    Google Scholar 

  31. Sabir, E., AbdAlmageed, W., Wu, Y., Natarajan, P.: Deep multimodal image-repurposing detection. In: 2018 ACM Multimedia Conference on Multimedia Conference, pp. 1337–1345. ACM (2018)

    Google Scholar 

  32. Shu, K., Mahudeswaran, D., Wang, S., Lee, D., Liu, H.: Fakenewsnet: a data repository with news content, social context and dynamic information for studying fake news on social media. arXiv preprint arXiv:1809.01286 (2018)

    Google Scholar 

  33. Shu, K., Sliva, A., Wang, S., Tang, J., Liu, H.: Fake news detection on social media: a data mining perspective. ACM SIGKDD Explor. Newsletter 19(1), 22–36 (2017)

    Article  Google Scholar 

  34. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

    Google Scholar 

  35. Sun, S., Liu, H., He, J., Du, X.: Detecting event rumors on Sina Weibo automatically. In: Asia-Pacific Web Conference, pp. 120–131. Springer (2013)

    Google Scholar 

  36. Sunstein, C.R.: On Rumors: How Falsehoods Spread, Why We Believe Them, and What Can Be Done. Princeton University Press, Princeton (2014)

    Book  Google Scholar 

  37. Wang, W., Farid, H.: Exposing digital forgeries in video by detecting double MPEG compression. In: Proceedings of the 8th Workshop on Multimedia and Security, pp. 37–47. ACM (2006)

    Google Scholar 

  38. Wang, W., Farid, H.: Exposing digital forgeries in video by detecting double quantization. In: Proceedings of the 11th ACM Workshop on Multimedia and Security, pp. 39–48. ACM (2009)

    Google Scholar 

  39. Wang, W.Y.: “Liar, liar pants on fire”: a new benchmark dataset for fake news detection. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 422–426 (2017)

    Google Scholar 

  40. Wang, Y., Ma, F., Jin, Z., Yuan, Y., Xun, G., Jha, K., Su, L., Gao, J.: Eann: event adversarial neural networks for multi-modal fake news detection. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 849–857. ACM (2018)

    Google Scholar 

  41. Wang, Z., Sheikh, H.R., Bovik, A.C.: No-reference perceptual quality assessment of jpeg compressed images. In: Proceedings. International Conference on Image Processing, vol. 1, pp. I–I. IEEE (2002)

    Google Scholar 

  42. Wu, K., Yang, S., Zhu, K.Q.: False rumors detection on Sina Weibo by propagation structures. In: 2015 IEEE 31st International Conference on Data Engineering, pp. 651–662. IEEE (2015)

    Google Scholar 

  43. Yang, F., Liu, Y., Yu, X., Yang, M.: Automatic detection of rumor on Sina Weibo. In: Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics. p. 13. ACM (2012)

    Google Scholar 

  44. Yang, X., Li, Y., Lyu, S.: Exposing deep fakes using inconsistent head poses. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8261–8265. IEEE (2019)

    Google Scholar 

  45. Zampoglou, M., Papadopoulos, S., Kompatsiaris, Y., Bouwmeester, R., Spangenberg, J.: Web and social media image forensics for news professionals. In: Tenth International AAAI Conference on Web and Social Media (2016)

    Google Scholar 

  46. Zhang, D.Y., Shang, L., Geng, B., Lai, S., Li, K., Zhu, H., Amin, M.T., Wang, D.: Fauxbuster: a content-free fauxtography detector using social media comments. In: 2018 IEEE International Conference on Big Data (Big Data), pp. 891–900. IEEE (2018)

    Google Scholar 

  47. Zhao, X., Li, J., Li, S., Wang, S.: Detecting digital image splicing in chroma spaces. In: International Workshop on Digital Watermarking, pp. 12–22. Springer (2010)

    Google Scholar 

  48. Zlatkova, D., Nakov, P., Koychev, I.: Fact-checking meets fauxtography: verifying claims about images. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 2099–2108 (2019)

    Google Scholar 

  49. Zubiaga, A., Aker, A., Bontcheva, K., Liakata, M., Procter, R.: Detection and resolution of rumours in social media: a survey. ACM Comput. Surv. (CSUR) 51(2), 32 (2018)

    Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China (U1703261).

Author information

Authors and Affiliations

  1. Key Laboratory of Intelligent Information Processing & Center for Advanced Computing Research, Institute of Computing Technology, CAS, Beijing, China

    Juan Cao, Peng Qi, Qiang Sheng, Tianyun Yang, Junbo Guo & Jintao Li

  2. University of Chinese Academy of Sciences, Huairou, China

    Juan Cao, Peng Qi, Qiang Sheng & Tianyun Yang

Authors
  1. Juan Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Peng Qi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qiang Sheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tianyun Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Junbo Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jintao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Juan Cao .

Editor information

Editors and Affiliations

  1. Computer Science & Engineering, Arizona State University, Tempe, AZ, USA

    Kai Shu

  2. College of Information Sciences and Technology, The Pennsylvania State University, University Park, PA, USA

    Suhang Wang

  3. College of Information Sciences and Technology, The Pennsylvania State University, University Park, PA, USA

    Dongwon Lee

  4. Computer Science & Engineering, Arizona State University, Tempe, AZ, USA

    Huan Liu

Appendix

Appendix

1.1 5 Data Repositories

The step above all to detect fake news is to collect a real-world benchmark dataset. Though several text-based fake news datasets [25, 39] have been released, publicized multimedia fake news datasets remain rare, hindering the development of fake multimedia news detection. We here introduce representative multimedia datasets in fake news detection as follows.

MediaEval-VMU Footnote 12: The earliest publicly available multimedia verification corpus originates from the MediaEval 2015 Verifying Multimedia Use (VMU) task [3], which is further extended in 2016 [5]. In the latest version, the dataset consists of tweets from Twitter related to 17 events (or hoaxes) that comprise in total 193 cases of real images, 218 cases of misused (fake) images and two cases of misused videos, associated with 6,225 real and 9,404 fake tweets posted by 5,895 and 9,025 unique users, respectively.

TMM17: Due to the insufficiency of images in previous works like VMU, Jin et al. [17] collected a new dataset by crawling posts related to the authoritatively verified events from Weibo. The dataset is constituted of 146 news events with 50,287 posts posted by 42,441 distinct users. A total of 25,953 images are attached to 19,762 of the posts. Note that this work focuses on event-level detection, so there exist posts with no image attached.

MM17[15]: This multimedia dataset is especially for multi-modal fake news detection. The authors used similar sources as [17], but text-only posts and posts with duplicated, small-size and large-height images were removed. The dataset finally consists of 9,528 posts, with balanced amounts of fake and real news.

FakeNewsNet Footnote 13: In [32], Shu et al. collected fake news articles instead of short statements by traversing the fact-check websites such as PolitiFactFootnote 14 and GossipCopFootnote 15 and then searching for the web pages of corresponding articles. Totally, 336 fake and 447 real news articles contain images in PolitiFact part, while 1,650 fake and 16,767 real do in GossipCop part.

MCG-FNeWS Footnote 16[8]: The first version of this dataset was released for the False News Detection Competition 2019. The data was collected from Weibo official debunking centerFootnote 17 and news verification system AI-ShiyaoFootnote 18 and reorganized for different sub-tasks in the competition. For multi-modal detection sub-task, the whole set consists of 46,373 posts (23,186 real and 23,187 fake) with 41,937 images (24,794 in real posts and 17,170 in fake posts).

EMNLP19 Footnote 19 [48]: This dataset is especially for verifying the claims about images. The image-related news was collected from two sources: A section of Snopes.com named Fauxtography Footnote 20 for all false image-related news and a small fraction of true news; Reuters’ Picture of the Year from 2015 to 2018 for most of true news. In total, this dataset contains 592 true and 641 false image-claim pairs.

1.2 5 Tools

In addition to methods, tools to verify the visual content of fake news online is valuable due to its convenience to non-technical users. In this subsection, we introduce some publicly available tools for multimedia content verification.

Google Reverse Image Search: A service of searching by an image from Google. The verifiers may upload the image or input the image URL to find similar images as well as the web pages containing them. Other substitutions like Baidu Images,Footnote 21 provide similar service.

FotoForensics Footnote 22: A website for forensics analysis of JPEG or PNG image, providing information including error level, hidden pixels, metadata and JPEG quality. Over 3.3 million images were analyzed by the service so far.

Image Verification Assistant Footnote 23: A website to analyze the veracity of online media supported by REVEAL project. For an image, it extracts and visualizes the metadata and detects various types of forensics features, such as double JPEG quantization, JPEG Ghosts, JPEG blocking artifact, error level analysis, high-frequency noise and median filtering noise residue.

Fake Video News Debunker Footnote 24: A free plugin that runs in Google Chrome or FireFox to verify videos and images. This integrated plugin provides service to obtain contextual information from Youtube or Facebook, extract keyframes for reverse image search, list the metadata and perform forensic analysis.

1.3 5 Relevant Competitions

To attract the attention from academia and industry and further promote the development of detection technology, considerable competitions for fake news detection were held but very few of them provided visual contents. Here, we introduce two competitions where visual contents can be exploited.

Verifying Multimedia Use (VMU): A part of the MediaEval Benchmark in 2015[3] and 2016[5], dealing with the automatic detection of manipulation and misuse of web multimedia content. A fake tweet was defined as a tweet that shared multimedia content inconsistent with the event it referred to. In 2015, participants were asked to predict the veracity (fake, real or unknown), given a tweet and the accompanying multimedia item (image or video) from an event. In 2016, a new related sub-task was added to detect image tampering.

False News Detection Competition 2019 Footnote 25: A competition held for false news detection on Weibo, with three sub-tasks: text-only, image-only and multi-modal detection. In image-only detection, models had to predict whether the image was attached to a false news post. In multi-modal detection, text, images and user profiles were all available to predict the veracity of the post.

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Cao, J., Qi, P., Sheng, Q., Yang, T., Guo, J., Li, J. (2020). Exploring the Role of Visual Content in Fake News Detection. In: Shu, K., Wang, S., Lee, D., Liu, H. (eds) Disinformation, Misinformation, and Fake News in Social Media. Lecture Notes in Social Networks. Springer, Cham. https://doi.org/10.1007/978-3-030-42699-6_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-42699-6_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-42698-9

  • Online ISBN: 978-3-030-42699-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation