Abstract
While spreading fake news is an old phenomenon, today social media enables misinformation to instantaneously reach millions of people. Content-based approaches to detect fake news, typically based on automatic text checking, are limited. It is indeed difficult to come up with general checking criteria. Moreover, once the criteria are known to an adversary, the checking can be easily bypassed. On the other hand, it is practically impossible for humans to check every news item, let alone preventing them from becoming viral.
We present Credulix, the first content-agnostic system to prevent fake news from going viral. Credulix is implemented as a plugin on top of a social media platform and acts as a vaccine. Human fact-checkers review a small number of popular news items, which helps us estimate the inclination of each user to share fake news. Using the resulting information, we automatically estimate the probability that an unchecked news item is fake. We use a Bayesian approach that resembles Condorcet’s Theorem to compute this probability. We show how this computation can be performed in an incremental, and hence fast manner.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Some news items are indeed seen by millions, and are easy to check a posteriori. For instance, according to CNN [1], the following fake news items were read by millions: “Thousands of fraudulent ballots for Clinton uncovered”; “Elizabeth Warren endorsed Bernie Sanders”; “The NBA cancels 2017 All-Star Game in North Carolina”.
- 2.
Naive Bayes approaches [32, 36] assume that the random variables are independent, even if they are not totally independent in practice. This enables to simplify a problem that, otherwise, would be far too complex to tackle. Naive Bayes approaches work surprisingly well in many complex real-world situations, and are also very robust [32] ([36] explains some possible theoretical reasons for this). Here, the imprecision of the probability we compute is compensated by the fact that we choose a threshold which is extremely close to 1 (i.e., \(1 - 10^{-6}\), or \(99.9999\%\)). Thus, even with an error of \(\times 100\), the actual probability would be \(1 - 10^{-4}\), with does not change much from our perspective.
- 3.
Our truth and falsehood criteria here are as good as the fact-checking team. Credulix trusts the fact-checking team to correctly identify true and false news items.
- 4.
One half as the optimal fraction of fake items in the ground truth is confirmed by our experiments.
References
http://www.zettasphere.com/mind-boggling-stats-for-1-second-of-internet-activity/
https://techcrunch.com/2018/01/19/facebooks-news-feed-update-trusted-sources
Cassandra. http://cassandra.apache.org/
Documentcloud. https://www.documentcloud.org/
Open calais. http://opencalais.com/
Twissandra Twitter clone, build on top of cassandra. https://github.com/twissandra/twissandra/
Austen-Smith, D., Banks, J.S.: Information aggregation, rationality, and the condorcet jury theorem (1996)
Balmau, O., Guerraoui, R., Kermarrec, A.M., Maurer, A., Pavlovic, M., Zwaenepoel, W.: Limiting the spread of fake news on social media platforms by evaluating users’ trustworthiness. arXiv preprint arXiv:1808.09922 (2018)
Ciampaglia, G.L., Shiralkar, P., Rocha, L.M., Bollen, J., Menczer, F., Flammini, A.: Computational fact checking from knowledge networks. PLoS One 10, e0128193 (2015)
Dewan, P., Kumaraguru, P.: Towards automatic real time identification of malicious posts on facebook. In: PST (2015)
Gupta, A., Kumaraguru, P.: Credibility ranking of tweets during high impact events. In: PSOSM (2012)
Gupta, A., Kumaraguru, P., Castillo, C., Meier, P.: TweetCred: real-time credibility assessment of content on Twitter. In: Aiello, L.M., McFarland, D. (eds.) SocInfo 2014. LNCS, vol. 8851, pp. 228–243. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-13734-6_16
Gupta, A., Lamba, H., Kumaraguru, P., Joshi, A.: Faking sandy: characterizing and identifying fake images on twitter during hurricane sandy. In: WWW (2013)
Imran, M., Castillo, C., Diaz, F., Vieweg, S.: Processing social media messages in mass emergency: a survey. ACM CSUR (2015)
Jenders, M., Kasneci, G., Naumann, F.: Analyzing and predicting viral tweets. In: WWW Companion (2013)
Kim, J., Tabibian, B., Oh, A., Schölkopf, B., Gomez Rodriguez, M.: Leveraging the crowd to detect and reduce the spread of fake news and misinformation. In: WSDM (2018)
Koch, K.R.: Bayes’ theorem. In: Bayesian Inference with Geodetic Applications (1990)
Kolari, P., Java, A., Finin, T., Oates, T., Joshi, A.: Detecting spam blogs: a machine learning approach. In: AAAI (2006)
Kwak, H., Lee, C., Park, H., Moon, S.: What is Twitter, a social network or a news media? In: WWW (2010)
Leskovec, J., Krevl, A.: SNAP datasets: stanford large network dataset collection. http://snap.stanford.edu/data (2014)
Markines, B., Cattuto, C., Menczer, F.: Social spam detection. In: AIRWeb (2009)
Resnick, P., Kuwabara, K., Zeckhauser, R., Friedman, E.: Reputation systems. Commun. ACM 43, 45–48 (2000)
Resnick, P., Varian, H.R.: Recommender systems. Commun. ACM 40, 56–59 (1997)
Rish, I.: An empirical study of the naïve bayes classifier. In: IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, vol. 3, January 2001
Saikaew, K.R., Noyunsan, C.: Features for measuring credibility on facebook information. Int. Sch. Sci. Res. Innov. 9, 174–177 (2015)
Viviani, M., Pasi, G.: A multi-criteria decision making approach for the assessment of information credibility in social media. In: Petrosino, A., Loia, V., Pedrycz, W. (eds.) WILF 2016. LNCS (LNAI), vol. 10147, pp. 197–207. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52962-2_17
Zabell, S.L.: The rule of succession. Erkenntnis 31, 283–321 (1989)
Zhang, H.: The optimality of naive bayes. In: Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference, pp. 562–567 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Balmau, O., Guerraoui, R., Kermarrec, AM., Maurer, A., Pavlovic, M., Zwaenepoel, W. (2019). The Fake News Vaccine. In: Atig, M., Schwarzmann, A. (eds) Networked Systems. NETYS 2019. Lecture Notes in Computer Science(), vol 11704. Springer, Cham. https://doi.org/10.1007/978-3-030-31277-0_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-31277-0_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31276-3
Online ISBN: 978-3-030-31277-0
eBook Packages: Computer ScienceComputer Science (R0)