Got TweetCred? Use it To Automatically Identify Credible Tweets (Updated)

Update: Users have created an astounding one million+ tags over the past few weeks, which will help increase the accuracy of TweetCred in coming months as we use these tags to further train our machine learning classifiers. We will be releasing our Firefox plugin in the next few days. In the meantime, we have just released our paper on TweetCred which describes our methodology & classifiers in more detail.

What if there were a way to automatically identify credible tweets during major events like disasters? Sounds rather far-fetched, right? Think again.

The new field of Digital Information Forensics is increasingly making use of Big Data analytics and techniques from artificial intelligence like machine learning to automatically verify social media. This is how my QCRI colleague ChaTo et al. already predicted both credible and non-credible tweets generated after the Chile Earthquake (with an accuracy of 86%). Meanwhile, my colleagues Aditi, et al. from IIIT Delhi also used machine learning to automatically rank the credibility of some 35 million tweets generated during a dozen major international events such as the UK Riots and the Libya Crisis. So we teamed up with Aditi et al. to turn those academic findings into TweetCred, a free app that identifies credible tweets automatically.

CNN TweetCred

We’ve just launched the very first version of TweetCred—key word being first. This means that our new app is still experimental. On the plus side, since TweetCred is powered by machine learning, it will become increasingly accurate over time as more users make use of the app and “teach” it the difference between credible and non-credible tweets. Teaching TweetCred is as simple as a click of the mouse. Take the tweet below, for example.

ARC TweetCred Teach

TweetCred scores each tweet based based on a 7-point system, the higher the number of blue dots, the more credible the content of the tweet is likely to be. Note that a TweetCred score also takes into account any pictures or videos included in a tweet along with the reputation and popularity of the Twitter user. Naturally, TweetCred won’t always get it right, which is where the teaching and machine learning come in. The above tweet from the American Red Cross is more credible than three dots would suggest. So you simply hover your mouse over the blue dots and click on the “thumbs down” icon to tell TweetCred it got that tweet wrong. The app will then ask you to tag the correct level of credibility for that tweet is.

ARC TweetCred Teach 3

That’s all there is to it. As noted above, this is just the first version of TweetCred. The more all of us use (and teach) the app, the more accurate it will be. So please try it out and spread the word. You can download the Chrome Extension for TweetCred here. If you don’t use Chrome, you can still use the browser version here although the latter has less functionality. We very much welcome any feedback you may have, so simply post feedback in the comments section below. Keep in mind that TweetCred is specifically designed to rate the credibility of disaster/crisis related tweets rather than any random topic on Twitter.

As I note in my book Digital Humanitarians (forthcoming), empirical studies have shown that we’re less likely to spread rumors on Twitter if false tweets are publicly identified by Twitter users as being non-credible. In fact, these studies show that such public exposure increases the number of Twitter users who then seek to stop the spread of said of rumor-related tweets by 150%. But, it makes a big difference whether one sees the rumors first or the tweets dismissing said rumors first. So my hope is that TweetCred will help accelerate Twitter’s self-correcting behavior by automatically identifying credible tweets while countering rumor-related tweets in real-time.

This project is a joint collaboration between IIIT and QCRI. Big thanks to Aditi and team for their heavy lifting on the coding of TweetCred. If the experiments go well, my QCRI colleagues and I may integrate TweetCred within our AIDR (Artificial Intelligence for Disaster Response) and Verily platforms.


See also:

  • New Insights on How to Verify Social Media [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]
  • Truth in the Age of Social Media: A Big Data Challenge [link]
  • Analyzing Fake Content on Twitter During Boston Bombings [link]
  • How to Verify Crowdsourced Information from Social Media [link]
  • Crowdsourcing Critical Thinking to Verify Social Media [link]
  • Tweets, Crises and Behavioral Psychology: On Credibility and Information Sharing [link]

16 responses to “Got TweetCred? Use it To Automatically Identify Credible Tweets (Updated)

  1. Fascinating and well worth the effort. If you haven’t seen this information, you might want to take a look.

  2. Whats to stop people from using this system to create cred for their stories? downvoting for example the tweets from your opponents, done in mass, can generate misinformation. I can imagine Republicans and Democrats in the USA for example using this to discredit each other

  3. Pingback: Lies are everywhere on the Internet. But this free tool could potentially fight them.

  4. Pingback: TweetCred: Chrome extension that rates Credibility of Tweets on Twitter - GoogStack

  5. Pingback: The Function of Social Media in Breaking News | The Function of Social Media in Breaking News

  6. Pingback: 備忘録:災害時にはやはり重要性を増すことを痛感。ツイッター関連情報 | - ソーシャルカンパニー

  7. Hey! A few questions:

    I installed the plug-in but I’m still trying to figure out how this works by seeing how it’s rating tweets in my feed. I’m wondering how exactly to rate things because, for example, my friend tweeted a picture of us working on a Google Hangout. It’s nothing special, but it has a rating of two stars. Is it relevant to anything or connected to an official source? No, but it is also a legitimate post from a legitimate source. So would I help or hurt the program by changing its rating to something higher or should I leave it alone?

    Also, when rating is it fair to assess that folks will either give it all 7 stars or 0 stars? I assume posts to individuals are either going to be credible or not, but does that extreme throw things off? And what do people do with the tweets that are viewed as credible? People who aren’t using the system won’t know the difference and will judge the credibility based on who initially shared it, who shared it with them, and how many tweets and favorites it’s received. I guess I’m curious on how you want to integrate it into emergency response. I can see some ties to my VOST team for something like this, but I don’t know how to pull credible data out and sort through it during a disaster.


  8. Thanks for your feedback Tanya! Definitely the questions you are asking are very valid. This is the first version of TweetCred that we have launched, we hope to make it better and more accurate with time and more user feedback.

    The TweetCred score take into account about 45 different features, like tweet, user and URL properties. So, the way the algorithm works currently, a post by your friend with your picture should get a medium credibility, since its posted by a valid Twitter user, yet since its not from a ‘known’ source, the algorithm cannot judge with 100% certainty that its valid.

    In future iterations we aim to make TweetCred customizable for users, that is you can train your version of TweetCred that who according to you is credible and who not, and it would show the results accordingly in future. Though, this is not implemented in the current version.

    During emergency response, we feel TweetCred can be useful, since it can help us filter out information that is definitely credible (high credibility) and should be used immediately v/s that information (low credibility) which we should double check and then consume. It narrows down our set of information to validate. Secondly, it can deter spread of fake information, as users can get a warning that some picture / video coming with very low credibility should not be trusted and propagated further.

  9. Pingback: Nieuwe tool toont betrouwbaarheid van elk Twitteraccount | Twittermania

  10. Pingback: The Function of Social Media in Breaking News | The Function of Social Media in Breaking News

  11. Pingback: Hey, is anybody watching Facebook? | Is Nerd

  12. But it seems to works only in the network of people who have install this TweetCred, if legitimate user has posted some information and if i want ot test its credibility then i will get low score because it has not entered in the network of TweetCred. How do you respond for this


  13. Hi Devraj,
    The credibility score provided by TweetCred is based on a generic model for any tweet, it is not restricted or dependent on users in the TweetCred network. The low credibility score for a particular tweet would be for other reasons. A user can choose not install TweetCred Plugin and still obtain credibility score for tweets using the API.

    You can read more about the research here:

    Please feel to write to us in case you need more details.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s