Tag Archives: Fake

Analyzing Fake Content on Twitter During Boston Marathon Bombings

As iRevolution readers already know, the application of Information Forensics to social media is one of my primary areas of interest. So I’m always on the lookout for new and related studies, such as this one (PDF), which was just published by colleagues of mine in India. The study by Aditi Gupta et al. analyzes fake content shared on Twitter during the Boston Marathon Bombings earlier this year.

bostonstrong

Gupta et al. collected close to 8 million unique tweets posted by 3.7 million unique users between April 15-19th, 2013. The table below provides more details. The authors found that rumors and fake content comprised 29% of the content that went viral on Twitter, while 51% of the content constituted generic opinions and comments. The remaining 20% relayed true information. Interestingly, approximately 75% of fake tweets were propagated via mobile phone devices compared to true tweets which comprised 64% of tweets posted via mobiles.

Table1 Gupta et al

The authors also found that many users with high social reputation and verified accounts were responsible for spreading the bulk of the fake content posted to Twitter. Indeed, the study shows that fake content did not travel rapidly during the first hour after the bombing. Rumors and fake information only goes viral after Twitter users with large numbers of followers start propagating the fake content. To this end, “determining whether some information is true or fake, based on only factors based on high number of followers and verified accounts is not possible in the initial hours.”

Gupta et al. also identified close to 32,000 new Twitter accounts created between April 15-19 that also posted at least one tweet about the bombings. About 20% (6,073 accounts) of these new accounts were subsequently suspended by Twitter. The authors found that 98.7% of these suspended accounts did not include the word Boston in their names and usernames. They also note that some of these deleted accounts were “quite influential” during the Boston tragedy. The figure below depicts the number of suspended Twitter accounts created in the hours and days following the blast.

Figure 2 Gupta et al

The authors also carried out some basic social network analysis of the suspended Twitter accounts. First, they removed from the analysis all suspended accounts that did not interact with each other, which left just 69 accounts. Next, they analyzed the network typology of these 69 accounts, which produced four distinct graph structures: Single Link, Closed Community, Star Typology and Self-Loops. These are displayed in the figure below (click to enlarge).

Figure 3 Gupta et al

The two most interesting graphs are the Closed Community and Star Typology graphs—the second and third graphs in the figure above.

Closed Community: Users that retweet and mention each other, forming a closed community as indicated by the high closeness centrality values produced by the social network analysis. “All these nodes have similar usernames too, all usernames have the same prefix and only numbers in the suffixes are different. This indicates that either these profiles were created by same or similar minded people for posting common propaganda posts.” Gupta et al. analyzed the content posted by these users and found that all were “tweeting the same propaganda and hate filled tweet.”

Star Typology: Easily mistakable for the authentic “BostonMarathon” Twitter account, the fake account “BostonMarathons” created plenty of confusion. Many users propagated the fake content posted by the BostonMarathons account. As the authors note, “Impersonation or creating fake profiles is a crime that results in identity theft and is punishable by law in many countries.”

The automatic detection of these network structures on Twitter may enable us to detect and counter fake content in the future. In the meantime, my colleagues and I at QCRI are collaborating with Aditi Gupta et al. to develop a “Credibility Plugin” for Twitter based on this analysis and earlier peer-reviewed research carried out by my colleague ChaTo. Stay tuned for updates.

Bio

See also:

  • Boston Bombings: Analyzing First 1,000 Seconds on Twitter [link]
  • Taking the Pulse of the Boston Bombings on Twitter [link]
  • Predicting the Credibility of Disaster Tweets Automatically [link]
  • Auto-Ranking Credibility of Tweets During Major Events [link]
  • Auto-Identifying Fake Images on Twitter During Disasters [link]
  • How to Verify Crowdsourced Information from Social Media [link]
  • Crowdsourcing Critical Thinking to Verify Social Media [link]

Automatically Identifying Fake Images Shared on Twitter During Disasters

Artificial Intelligence (AI) can be used to automatically predict the credibility of tweets generated during disasters. AI can also be used to automatically rank the credibility of tweets posted during major events. Aditi Gupta et al. applied these same information forensics techniques to automatically identify fake images posted on Twitter during Hurricane Sandy. Using a decision tree classifier, the authors were able to predict which images were fake with an accuracy of 97%. Their analysis also revealed retweets accounted for 86% of all tweets linking to fake images. In addition, their results showed that 90% of these retweets were posted by just 30 Twitter users.

Fake Images

The authors collected the URLs of fake images shared during the hurricane by drawing on the UK Guardian’s list and other sources. They compared these links with 622,860 tweets that contained links and the words “Sandy” & “hurricane” posted between October 20th and November 1st, 2012. Just over 10,300 of these tweets and retweets contained links to URLs of fake images while close to 5,800 tweets and retweets pointed to real images. Of the ~10,300 tweets linking to fake images, 84% (or 9,000) of these were retweets. Interestingly, these retweets spike about 12 hours after the original tweets are posted. This spike is driven by just 30 Twitter users. Furthermore, the vast majority of retweets weren’t made by Twitter followers but rather by those following certain hashtags. 

Gupta et al. also studied the profiles of users who tweeted or retweeted fake images  (User Features) and also the content of their tweets (Tweet Features) to determine whether these features (listed below) might be predictive of whether a tweet posts to a fake image. Their decision tree classifier achieved an accuracy of over 90%, which is remarkable. But the authors note that this high accuracy score is due to “the similar nature of many tweets since since a lot of tweets are retweets of other tweets in our dataset.” In any event, their analysis also reveals that Tweet-based Features (such as length of tweet, number of uppercase letters, etc.), were far more accurate in predicting whether or not a tweeted image was fake than User-based Features (such as number of friends, followers, etc.). One feature that was overlooked, however, is gender.

Information Forensics

In conclusion, “content and property analysis of tweets can help us in identifying real image URLs being shared on Twitter with a high accuracy.” These results reinforce the proof that machine computing and automated techniques can be used for information forensics as applied to images shared on social media. In terms of future work, the authors Aditi Gupta, Hemank Lamba, Ponnurangam Kumaraguru and Anupam Joshi plan to “conduct a larger study with more events for identification of fake images and news propagation.” They also hope to expand their study to include the detection of “rumors and other malicious content spread during real world events apart from images.” Lastly, they “would like to develop a browser plug-in that can detect fake images being shared on Twitter in real-time.” There full paper is available here.

Needless to say, all of this is music to my ears. Such a plugin could be added to our Artificial Intelligence for Disaster Response (AIDR) platform, not to mention our Verily platform, which seeks to crowdsource the verification of social media reports (including images and videos) during disasters. What I also really value about the authors’ approach is how pragmatic they are with their findings. That is, by noting their interest in developing a browser plugin, they are applying their data science expertise for social good. As per my previous blog post, this focus on social impact is particularly rare. So we need more data scientists like Aditi Gupta et al. This is why I was already in touch with Aditi last year given her research on automatically ranking the credibility of tweets. I’ve just reached out to her again to explore ways to collaborate with her and her team.

bio

Comparing the Quality of Crisis Tweets Versus 911 Emergency Calls

In 2010, I published this blog post entitled “Calling 911: What Humanitarians Can Learn from 50 Years of Crowdsourcing.” Since then, humanitarian colleagues have become increasingly open to the use of crowdsourcing as a methodology to  both collect and process information during disasters.  I’ve been studying the use of twitter in crisis situations and have been particularly interested in the quality, actionability and credibility of such tweets. My findings, however, ought to be placed in context and compared to other, more traditional, reporting channels, such as the use of official emergency telephone numbers. Indeed, “Information that is shared over 9-1-1 dispatch is all unverified information” (1).

911ex

So I did some digging and found the following statistics on 911 (US) & 999 (UK) emergency calls:

  • “An astounding 38% of some 10.4 million calls to 911 [in New York City] during 2010 involved such accidental or false alarm ‘short calls’ of 19 seconds or less — that’s an average of 10,700 false calls a day”.  – Daily News
  • “Last year, seven and a half million emergency calls were made to the police in Britain. But fewer than a quarter of them turned out to be real emergencies, and many were pranks or fakes. Some were just plain stupid.” – ABC News

I also came across the table below in this official report (PDF) published in 2011 by the European Emergency Number Association (EENA). The Greeks top the chart with a staggering 99% of all emergency calls turning out to be false/hoaxes, while Estonians appear to be holier than the Pope with less than 1% of such calls.

Screen Shot 2012-12-11 at 4.45.34 PM

Point being: despite these “data quality” issues, European law enforcement agencies have not abandoned the use of emergency phone numbers to crowd-source the reporting of emergencies. They are managing the challenge since the benefit of these number still far outweigh the costs. This calculus is unlikely to change as law enforcement agencies shift towards more mobile-based solutions like the use of SMS for 911 in the US. This important shift may explain why tra-ditional emergency response outfits—such as London’s Fire Brigade—are putting in place processes that will enable the public to report via Twitter.

For more information on the verification of crowdsourced social media informa-tion for disaster response, please follow this link.

What Was Novel About Social Media Use During Hurricane Sandy?

We saw the usual spikes in Twitter activity and the typical (reactive) launch of crowdsourced crisis maps. We also saw map mashups combining user-generated content with scientific weather data. Facebook was once again used to inform our social networks: “We are ok” became the most common status update on the site. In addition, thousands of pictures where shared on Instagram (600/minute), documenting both the impending danger & resulting impact of Hurricane Sandy. But was there anything really novel about the use of social media during this latest disaster?

I’m asking not because I claim to know the answer but because I’m genuinely interested and curious. One possible “novelty” that caught my eye was this FrankenFlow experiment to “algorithmically curate” pictures shared on social media. Perhaps another “novelty” was the embedding of webcams within a number of crisis maps, such as those below launched by #HurricaneHacker and Team Rubicon respectively.

Another “novelty” that struck me was how much focus there was on debunking false information being circulated during the hurricane—particularly images. The speed of this debunking was also striking. As regular iRevolution readers will know, “information forensics” is a major interest of mine.

This Tumblr post was one of the first to emerge in response to the fake pictures (30+) of the hurricane swirling around the social media whirlwind. Snopes.com also got in on the action with this post. Within hours, The Atlantic Wire followed with this piece entitled “Think Before You Retweet: How to Spot a Fake Storm Photo.” Shortly after, Alexis Madrigal from The Atlantic published this piece on “Sorting the Real Sandy Photos from the Fakes,” like the one below.

These rapid rumor-bashing efforts led BuzzFeed’s John Herman to claim that Twitter acted as a truth machine: “Twitter’s capacity to spread false information is more than cancelled out by its savage self-correction.” This is not the first time that journalists or researchers have highlighted Twitter’s tendency for self-correction. This peer-reviewed, data-driven study of disaster tweets generated during the 2010 Chile Earthquake reports the same finding.

What other novelties did you come across? Are there other interesting, original and creative uses of social media that ought to be documented for future disaster response efforts? I’d love to hear from you via the comments section below. Thanks!