Faking Sandy: characterizing and identifying fake images on Twitter during Hurricane Sandy

By Aditi Gupta, Hemank Lamba, Ponnurangam Kumaraguru, Anupam Joshi. The Web Conference, 2013

659 citations recorded by the source corpus.

Subfields: Information Systems, Sociology and Political Science, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/d2881731e12173bf70da724fb14bfb3a01044bb3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

1. Kai Shu
2. Neil Shah
3. Srijan Kumar
4. Carlos Castillo
5. Sarah Vieweg
6. Fernando Diaz
7. Muhammad Imran
8. Juan Cao

In Sociology and Political Science

1. Kai Shu
2. Carlos Castillo
3. Fernando Diaz
4. Neil Shah
5. Srijan Kumar
6. Muhammad Imran
7. Sarah Vieweg
8. Juan Cao

In Statistical and Nonlinear Physics

1. Carlos Castillo
2. Kai Shu
3. Muhammad Imran
4. Jure Leskovec
5. Fernando Diaz
6. Huan Liu
7. Sarah Vieweg
8. Xia Hu

Citations in the corpus

• Multimodal Fusion with Recurrent Neural Networks for Rumor Detection on Microblogs (2017, background): “Only a few recent studies make a first attempt to detect rumors based on multimedia content [9, 15, 16].”
• Real-time Rumor Debunking on Twitter (2015, background): “Early exploration of this problem started from two special case studies on rumor propagation during natural disasters like earthquakes and hurricanes[6, 3].”
• Enquiring Minds: Early Detection of Rumors in Social Media from Enquiry Posts (2015, background): “Application domains have included “event rumors” in Sun et al. [33], and fake images on Twitter during Hurricane Sandy [16].”
• False Information on Web and Social Media: A Survey (2018, methodology): “[32] used user features (number of friends, account age, etc.”
• Multi-label Adversarial Perturbations (2018, background): “It also motivates the explorations of generating powerful perturbations to analyze the vulnerability of machine learning models, detect their blind spots, and improve their robustness [8]–[10].”
• Novel Visual and Statistical Image Features for Microblogs News Verification (2017, background): “[23] make an effort to understand the temporal, social reputation and influence patterns for the spreading of fake images on mircoblogs.”
• Processing Social Media Messages in Mass Emergency (2014, background): “2013]; credible topics [Canini et al. 2011]; content credibility [Gupta and Kumaraguru 2012]; users and content credibility [Gupta et al. 2014]; source credibility [Thomson et al. 2012]; fake photos [Gupta et al. 2013] Rumors rumor [Hughes et al. 2014b; Castillo et al. 2013] By time Pre-phase/prepar”
• Cross-modal Ambiguity Learning for Multimodal Fake News Detection (2022, background): “both claimed that the spreading pattern of image content across a social platform exhibits discriminating features, which are suitable for fake image detection [10, 14].”
• Beyond News Contents: The Role of Social Context for Fake News Detection (2017, background): “Visual-based features try to identify fake images [9] that are intentionally created or capturing specific characteristics for images in fake news.”
• TweetCred: Real-Time Credibility Assessment of Content on Twitter (2014, background): “Misinformation and disinformation in social media, and particularly in Twitter, has been observed during major events that include the 2010 earthquake in Chile [12], the Hurricane Sandy in 2012 [10] and the Boston Marathon blasts in 2013 [9].”
• Fake images: The effects of source, intermediary, and digital media literacy on contextual assessment of image credibility online (2018, background): “Among the few empirical studies specifically on image credibility, for instance, Gupta et al. (2013) identified more than 10,000 tweets containing fake photos, and used machine learning models to compare fake images to real ones based on several features.”
• DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning (2018, methodology): “Approaches like (Castillo et al., 2011; Qazvinian et al., 2011; Yang et al., 2012; Xu and Zhao, 2012; Gupta et al., 2013; Zhao et al., 2015; Volkova et al., 2017) propose supervised methods for detecting deceptive content in social media platforms like Twitter, Sina Weibo, etc. Similarly,…”
• Fake News Identification on Twitter with Hybrid CNN and RNN Models (2018, background): “andy, where enormous amounts of fake and altered images were circulating on the internet. Gupta et al used a Decision Tree classifier to distinguish between fake and real images posted about the event[12]. Neural networks are a form of machine learning method that have been found to exhibit high acc”
• Science audiences, misinformation, and fake news (2019, background): “org have also emerged to boost people’s abilities to debunk misinformation (35), and efforts are ongoing to offer reliable, automated “deception detection” for both text and images (36, 37).”
• A Convolutional Approach for Misinformation Identification (2017, background): “org/2016/11/08/500686320/did-social-mediaruin-election-2016 Conventional misinformation identification models leverage handcrafted features from user credibility and microblog post2 content at post level [Castillo et al., 2011; Qazvinian et al., 2011; Gupta et al., 2013], at event3 level [Kwon et al”