Embedded Files
It's time to
We use Machine Learning and Artificial Intelligence to find, flag, and delete spam from your social accounts.
How it works
Open an account
Open an account
We only ask for the things we need to get going, nothing more. Just your email, password and your social accounts where you are getting spam. Later you can tinker with the settings if you want to.
Run the spam scanner
Run the spam scanner
Depending on how popular your social account is, this process can take several hours. But we'll keep you posted on the progress and you can see right away what's spam vs. ham.
Act on it
Act on it
You can either use our automated spam deletion, or you can manually delete the spam yourself. We'll monitor your account and alert you if we find any spam on your account.
The Problem: ELI5
(explain it like I'm 5)
If you used the internet at some point... you have seen the usual spam comment. The goal for the bad actor is usually to sell you something, to sell something to your subscribers or to lie to your audience. The social platforms have somewhat tried to prevent this but have ultimately failed, hence why you're here.
The goal of this project is to end spam. Period. It's not easy, because for every spam comment, post or picture you try to manually delete, hundreds or thousands more appear. Spam is generated by bots — automated computer programs that act as real people.
You can't fight them manually. A person is not as fast or efficient as a computer. That's where we come in. We are the anti-bots. The anti-spam. Our goal is to have a cleaner, safer, less disruptive experience on the web. We can't do it alone. We need you too. Using a service like this to end spam is the first step.
Our favorite content creators have been flagged as spammers because "the algorithm" from this social platforms don't do a good job at identifying who's the real spammer.
The Solution
(this is a simplified technical explanation, but there's a lot more going on behind the scenes)
Using the settings in these platforms to "hold for review" and "block" comments matching only keywords is not enough. There's a million ways to craft a spam message. We need Machine Learning to fight back at these annoying bots.
It's not an easy task. The AI model needs to be trained by humans (aka supervised learning) on a small data set by telling what's spam and what's ham (labeling). Then the algorithm is provided with data it has never seen before (not used in the training phase). A properly trained model will be able to use the experience from the training data to accurately label the new data.
The model has to be retrained every so often to account for new ways to craft spam. We take care of all of that, and package it in a simple and easy to use software-as-a-service (SAAS).
If you want to contribute to this project please contact us.
"We choose to go to the moon in this decade and do the other things, not because they are easy, but because they are hard, because that goal will serve to organize and measure the best of our energies and skills, because that challenge is one that we are willing to accept, one we are unwilling to postpone, and one which we intend to win, and the others, too."
— John F. Kennedy
Google Sites
Report abuse