Let’s talk about spam. And let’s do so with the benefit of data, facts, and context…
Conversation
First, let me state the obvious: spam harms the experience for real people on Twitter, and therefore can harm our business. As such, we are strongly incentivized to detect and remove as much spam as we possibly can, every single day. Anyone who suggests otherwise is just wrong.
Replying to
Next, spam isn’t just ‘binary’ (human / not human). The most advanced spam campaigns use combinations of coordinated humans + automation. They also compromise real accounts, and then use them to advance their campaign. So – they are sophisticated and hard to catch.
146
361
3,278
Some final context: fighting spam is incredibly *dynamic*. The adversaries, their goals, and tactics evolve constantly – often in response to our work! You can’t build a set of rules to detect spam today, and hope they will still work tomorrow. They will not.
86
285
3,033
We suspend over half a million spam accounts every day, usually before any of you even see them on Twitter. We also lock millions of accounts each week that we suspect may be spam – if they can’t pass human verification challenges (captchas, phone verification, etc).
287
650
3,776
The hard challenge is that many accounts which look fake superficially – are actually real people. And some of the spam accounts which are actually the most dangerous – and cause the most harm to our users – can look totally legitimate on the surface.
149
419
3,181
Our team updates our systems and rules constantly to remove as much spam as possible, without inadvertently suspending real people or adding unnecessary friction for real people when they use Twitter: none of us want to solve a captcha every time we use Twitter.
106
211
2,502
Now, we know we aren’t perfect at catching spam. And so this is why, after all the spam removal I talked about above, we know some still slips through. We measure this internally. And every quarter, we have estimated that <5% of reported mDAU for the quarter are spam accounts.
95
220
2,190
Our estimate is based on multiple human reviews (in replicate) of thousands of accounts, that are sampled at random, consistently over time, from *accounts we count as mDAUs*. We do this every quarter, and we have been doing this for many years.
65
204
2,111
Each human review is based on Twitter rules that define spam and platform manipulation, and uses both public and private data (eg, IP address, phone number, geolocation, client/browser signatures, what the account does when it’s active…) to make a determination on each account.
235
309
3,148
The use of private data is particularly important to avoid misclassifying users who are actually real. FirstnameBunchOfNumbers with no profile pic and odd tweets might seem like a bot or spam to you, but behind the scenes we often see multiple indicators that it’s a real person.
171
377
2,510
Our actual internal estimates for the last four quarters were all well under 5% – based on the methodology outlined above. The error margins on our estimates give us confidence in our public statements each quarter.
154
212
1,980
Unfortunately, we don’t believe that this specific estimation can be performed externally, given the critical need to use both public and private information (which we can’t share). Externally, it’s not even possible to know which accounts are counted as mDAUs on any given day.
1,024
589
3,715
There are LOTS of details that are very important underneath this high-level description. We shared an overview of the estimation process with Elon a week ago and look forward to continuing the conversation with him, and all of you.
324
217
2,075
For those of you who want to learn more in the meantime: blog.twitter.com/en_us/topics/c
blog.twitter.com/content/blog-t
618
428
2,344