Published in Blog

Welcome to a world where you need a Fake News Chatbot for Facebook Messenger

It’s the biggest crisis facing our democracy, the failing business model of real journalism,” Senator Claire McCaskill, Democrat of Missouri and a longtime critic of fake news, told me on Saturday. Ms. McCaskill said that “journalism is partly to blame” for being slow to adjust as the internet turned its business model upside down and social media opened the competitive floodgates. “Fake news got way out ahead of them,” she said.

NYTIMES: Media’s next challenge — overcoming the threat of fake news I found this excerpt and link here.

I see a world where you’re not afraid of opening the wrong link. So it makes perfect sense for MetaCert to give back, by building a Fake News Chatbot that helps society to avoid Fake News — leading to better informed decisions that impact the world around us.

The Fake News Chatbot is currently a “social experiment”. It does just one thing, but it does it well. Copy and paste a web link and the chatbot will tell you if it’s Fake News.

If it’s not fake, it’ll check to see if the link goes to a ‘Malware & Phishing’ or ‘Pornography’ website — so you’ll know if you need to proceed with caution. But again, we’re focused on Fake News with this bot — not the other categories — that extra protection is a bonus thrown in for good measure.

How do we know if a site is classified as Fake News?

MetaCert is not an expert at identifying Fake News. There are other credible organizations that do this well. And they publish their lists online. We use these credible and trusted sources to give intelligence to our chatbot. I’ll update this post with links to our sources soon when I’m happy we’ve covered them all.

What MetaCert is an expert at, is content labeling — otherwise known as URL Classification. In fact, MetaCert is the best in the world at this one thing — by a lot.

We have the world’s biggest threat intelligence system of classified URLs and our classification platform, has the ability to label sections of sites with user generated content — sites like Facebook and Twitter. For example, we can label Facebook Profile Pages that belong to Fake News sites. No other security company can do this today, and no Fake News-related, fact-checking organization has gone to the trouble of finding and listing Facebook Profile Pages (or Twitter profiles for that matter).

So, in the coming weeks we will seek, find and label every Facebook profile page that belongs to a classified Fake News site. We will then focus on Alt-Right websites and their profile pages. We’ve labeled for the purpose of testing to make sure our other news-related categories work as designed.

This is what I have to say to Fake News and Alt-Right websites and Facebook Profile Pages…

What next?

Today, we started the build of a new Chrome extension that will automatically remove all Fake News from your Facebook feed. It should be ready by the end of February for beta testing. Send an email to if you would like early access.

Then what?

Then we will work with Artificial Intelligence technologies and industry people, to help identify and learn from the patterns that these websites have in common. This will hopefully allow us to build even more intelligence inside our Chrome extension and chatbot so we don’t have to rely on people to fact check. But that’s some time away.

My ultimate goal

My ultimate goal is to use the chatbot and Chrome extension so show Facebook, Google and other news platforms/sources, how they can and should, use our API to remove Fake News from the Internet at scale. Our API is cloud-based and provides intelligence on over 10 billion URIs.

Er, what’s a chatbot?

If you’ve read this far and don’t know what a chatbot is, what were you thinking all this time? :)

Think of the Fake News chatbot as a mini app that you add to your Facebook Messenger app. The bot is added and listed as a contact. You type messages to the bot in the same way you would a person. But, this bot understands only one command — you’ve guessed it; “does this link go to a Fake News website?”. But, you don’t need to write all of that — just paste the link. There’s little point in trying to talk to the bot like a person, but you can try. We might give it a personality if enough people ask for one. But it would need to be the personality of an animal or thing — people are biased. Our bot is not biased.

Your privacy matters

The bot can’t read any message you send to anyone else in your contacts list. And it can’t read any messages you receive either — it’s technically impossible, and we wouldn’t do it even if it was possible. So, your privacy is safe with us and not in any way, compromised by this bot.

Please tap or click “♥︎” to help to promote this piece to others.

If you care about Fake News and agree that there is no place for it in our world, please help us spread the word by going to the Chatbot page on Facebook and share/like it.

You can talk to the chatbot from the Facebook page or you can click this link and add it directly to Messenger.



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Paul Walsh

Paul Walsh


MetaCert CEO. Passionate about Cybersecurity, Blockchain, Crypto, Snowboarding & Red Wine. Part of the AOL team that launched AIM. Co-founded 2 W3C Standards.