ABSTRACT
Our work considers leveraging crowd signals for detecting fake news and is motivated by tools recently introduced by Facebook that enable users to flag fake news. By aggregating users' flags, our goal is to select a small subset of news every day, send them to an expert (e.g., via a third-party fact-checking organization), and stop the spread of news identified as fake by an expert. The main objective of our work is to minimize the spread of misinformation by stopping the propagation of fake news in the network. It is especially challenging to achieve this objective as it requires detecting fake news with high-confidence as quickly as possible. We show that in order to leverage users' flags efficiently, it is crucial to learn about users' flagging accuracy. We develop a novel algorithm, DETECTIVE, that performs Bayesian inference for detecting fake news and jointly learns about users' flagging accuracy over time. Our algorithm employs posterior sampling to actively trade off exploitation (selecting news that maximize the objective value at a given epoch) and exploration (selecting news that maximize the value of information towards learning about users' flagging accuracy). We demonstrate the effectiveness of our approach via extensive experiments and show the power of leveraging community signals for fake news detection.
- Carlos Castillo, Marcelo Mendoza, and Barbara Poblete. 2011. Information credibility on twitter. In WWW. 675--684. Google ScholarDigital Library
- Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. In NIPS. 2249--2257. Google ScholarDigital Library
- Liang Chen, Zheng Yan, Weidong Zhang, and Raimo Kantola. 2015. TruSMS: a trustworthy SMS spam control system based on trust management. Future Generation Computer Systems Vol. 49 (2015), 77--93. Google ScholarDigital Library
- Yuxin Chen, Jean-Michel Renders, Morteza Haghir Chehreghani, and Andreas Krause. 2017. Efficient Online Learning for Optimizing Value of Information: Theory and Application to Interactive Troubleshooting. In UAI.Google Scholar
- Pern Hui Chia and Svein Johan Knapskog. 2011. Re-evaluating the wisdom of crowds in assessing web security International Conference on Financial Cryptography and Data Security. 299--314. Google ScholarDigital Library
- Giovanni Luca Ciampaglia, Prashant Shiralkar, Luis M Rocha, Johan Bollen, Filippo Menczer, and Alessandro Flammini. 2015. Computational fact checking from knowledge networks. PloS one Vol. 10, 6 (2015), e0128193.Google ScholarCross Ref
- Niall J Conroy, Victoria L Rubin, and Yimin Chen. 2015. Automatic deception detection: Methods for finding fake news. Proceedings of the Association for Information Science and Technology Vol. 52, 1 (2015), 1--4. Google ScholarCross Ref
- Nan Du, Le Song, Manuel Gomez-Rodriguez, and Hongyuan Zha. 2013. Scalable Influence Estimation in Continuous-Time Diffusion Networks NIPS. 3147--3155. Google ScholarDigital Library
- Stuart Ewen. 1998. PR!: a social history of spin. Basic Books.Google Scholar
- Facebook. 2016. News Feed FYI: Addressing Hoaxes and Fake News. texttthttps://newsroom.fb.com/news/2016/texttt12/news-feed-fyi-addressing-hoaxes-and-textttfake-news/. (December. 2016).Google Scholar
- Facebook. 2017. Umgang mit Falschmeldungen (Handling of false alarms). texttthttps://de.newsroom.fb.com/news/2017/texttt01/umgang-mit-falschmeldungen/. (January. 2017).Google Scholar
- David Mandell Freeman. 2017. Can You Spot the Fakes: On the Limitations of User Feedback in Online Social Networks WWW. 1093--1102. Google ScholarDigital Library
- Aditi Gupta, Ponnurangam Kumaraguru, Carlos Castillo, and Patrick Meier. 2014. Tweetcred: Real-time credibility assessment of content on twitter International Conference on Social Informatics. Springer, 228--243.Google Scholar
- Nguyen Quoc Viet Hung, Duong Chi Thang, Matthias Weidlich, and Karl Aberer. 2015. Minimizing efforts in validating crowd answers. In SIGMOD. 999--1014. Google ScholarDigital Library
- David Kempe, Jon Kleinberg, and Éva Tardos. 2003. Maximizing the spread of influence through a social network KDD. 137--146. Google ScholarDigital Library
- J. Kim, B. Tabibian, A. Oh, B. Schoelkopf, and M. Gomez-Rodriguez. 2018. Leveraging the Crowd to Detect and Reduce the Spread of Fake News and Misinformation WSDM '18: Proceedings of the 11th ACM International Conference on Web Search and Data Mining. Google ScholarDigital Library
- Srijan Kumar, Robert West, and Jure Leskovec. 2016. Disinformation on the web: Impact, characteristics, and detection of wikipedia hoaxes WWW. 591--602. Google ScholarDigital Library
- Sejeong Kwon, Meeyoung Cha, and Kyomin Jung. 2017. Rumor detection over varying time windows. PloS one Vol. 12, 1 (2017), e0168344.Google ScholarCross Ref
- Jure Leskovec and Julian J Mcauley. 2012. Learning to discover social circles in ego networks NIPS. 539--547. Google ScholarDigital Library
- Yaliang Li, Qi Li, Jing Gao, Lu Su, Bo Zhao, Wei Fan, and Jiawei Han. 2015. On the discovery of evolving truth. In KDD. 675--684. Google ScholarDigital Library
- Mengchen Liu, Liu Jiang, Junlin Liu, Xiting Wang, Jun Zhu, and Shixia Liu. 2017. Improving Learning-from-Crowds through Expert Validation IJCAI. 2329--2336. Google ScholarDigital Library
- Cristian Lumezanu, Nick Feamster, and Hans Klein. 2012. # bias: Measuring the tweeting behavior of propagandists AAAI Conference on Weblogs and Social Media.Google Scholar
- Tyler Moore and Richard Clayton. 2008. Evaluating the wisdom of crowds in assessing phishing websites. Lecture Notes in Computer Science Vol. 5143 (2008), 16--30.Google ScholarDigital Library
- Ian Osband, Dan Russo, and Benjamin Van Roy. 2013. (More) efficient reinforcement learning via posterior sampling NIPS. 3003--3011. Google ScholarDigital Library
- Poynter. 2016. International Fact-Checking Network: Fact-Checkers Code Principles. texttthttps://www.poynter.org/international- textttfact-checking-network-fact-checkers- textttcode-principles. (September. 2016).Google Scholar
- Marian-Andrei Rizoiu, Lexing Xie, Scott Sanner, Manuel Cebrián, Honglin Yu, and Pascal Van Hentenryck. 2017. Expecting to be HIP: Hawkes Intensity Processes for Social Media Popularity WWW. 735--744. Google ScholarDigital Library
- Victoria L Rubin, Yimin Chen, and Niall J Conroy. 2015. Deception detection for news: three types of fakes. Proceedings of the Association for Information Science and Technology Vol. 52, 1 (2015), 1--4. Google ScholarCross Ref
- Behzad Tabibian, Isabel Valera, Mehrdad Farajtabar, Le Song, Bernhard Schölkopf, and Manuel Gomez-Rodriguez. 2017. Distilling information reliability and source trustworthiness from digital traces WWW. 847--855. Google ScholarDigital Library
- William R Thompson. 1933. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika Vol. 25, 3/4 (1933), 285--294.Google ScholarCross Ref
- Hastagiri P Vanchinathan, Andreas Marfurt, Charles-Antoine Robelin, Donald Kossmann, and Andreas Krause. 2015. Discovering valuable items from massive data. In KDD. 1195--1204. Google ScholarDigital Library
- Svitlana Volkova, Kyle Shaffer, Jin Yea Jang, and Nathan Hodas. 2017. Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter. In ACL, Vol. Vol. 2. 647--653.Google Scholar
- Gang Wang, Manish Mohanlal, Christo Wilson, Xiao Wang, Miriam J. Metzger, Haitao Zheng, and Ben Y. Zhao. 2013. Social Turing Tests: Crowdsourcing Sybil Detection NDSS.Google ScholarDigital Library
- William Yang Wang. 2017. "Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection ACL. 422--426.Google Scholar
- Wei Wei and Xiaojun Wan. 2017. Learning to Identify Ambiguous and Misleading News Headlines IJCAI. 4172--4178. Google ScholarDigital Library
- Shu Wu, Qiang Liu, Yong Liu, Liang Wang, and Tieniu Tan. 2016. Information Credibility Evaluation on Social Media. AAAI. 4403--4404. Google ScholarDigital Library
- Bo Zhao, Benjamin IP Rubinstein, Jim Gemmell, and Jiawei Han. 2012. A bayesian approach to discovering truth from conflicting sources for data integration. Proceedings of the VLDB Endowment Vol. 5, 6 (2012), 550--561. Google ScholarDigital Library
- Qingyuan Zhao, Murat A. Erdogdu, Hera Y. He, Anand Rajaraman, and Jure Leskovec. 2015 a. SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity KDD. 1513--1522. Google ScholarDigital Library
- Zhe Zhao, Paul Resnick, and Qiaozhu Mei. 2015 b. Enquiring minds: Early detection of rumors in social media from enquiry posts WWW. 1395--1405. Google ScholarDigital Library
- Elena Zheleva, Aleksander Kolcz, and Lise Getoor. 2008. Trusting spam reporters: A reporter-based reputation system for email filtering. TOIS Vol. 27, 1 (2008), 3. Google ScholarDigital Library
Index Terms
- Fake News Detection in Social Networks via Crowd Signals
Recommendations
Fake news detection on social media via implicit crowd signals
WebMedia '19: Proceedings of the 25th Brazillian Symposium on Multimedia and the WebThe proliferation of Fake News on social media has been a source of widespread concern. One of the main approaches to automatically detect this type of news is based on crowd signals, i.e., opinions manifested by social media users concerning whether ...
Fake News Detection on Social Media: A Data Mining Perspective
Social media for news consumption is a double-edged sword. On the one hand, its low cost, easy access, and rapid dissemination of information lead people to seek out and consume news from social media. On the other hand, it enables the wide spread of \...
Fake News Early Detection: A Theory-driven Model
Field NotesMassive dissemination of fake news and its potential to erode democracy has increased the demand for accurate fake news detection. Recent advancements in this area have proposed novel techniques that aim to detect fake news by exploring how it ...
Comments