Making Progress on Spam

We’ve previously discussed our efforts to defend Twitter against spam. We are making progress—there are bugs while we find our way—but we’re making progress too. Recently, we’ve seen significant impact by introducing limits around how many accounts can be followed on Twitter under certain conditions. These limits are designed to not affect the vast majority of users. However, some people (who are not spammers) have (and will) run into them. We want to shed some light on what we’ve done and why.

A Work In Progress

First of all, let me note that these limits are still a work in progress. We’ve had some bugs in them that are still being worked out. And we need to tweak them to adapt to what we learn about our ever-changing system. However, it’s clear from our vantage point they’ve already had a very positive effect in reducing (though not eliminating) the most common type of Twitter abuse: “Follow spam.”

What is “Follow Spam?”

Follow spam is the act of following mass numbers of people, not because you’re actually interested in their tweets, but simply to gain attention, get views of your profile (and possibly clicks on URLs therein), or (ideally) to get followed back. Many people who are seeking to get attention in this way have even created programs to do the following on their behalf, which enable them to follow thousands of people at the blink of any eye.

As you can imagine, this is a problem. In extreme cases, these automated accounts have followed so many people they’ve threatened the performance of the entire system. In less-extreme cases, they simply annoy thousands of legitimate users who get an email about this new follower only to find out their interest may not be entirely…sincere. On rare occasions we may see a person who is mass following and actually cares about every tweet—there is an opportunity for us to learn more about this use case and work to provide a better experience.

There Is No Magic Number

So, our challenge is to curb this type of behavior without interfering with non-spammy users—some of whom may just be very enthusiastic followers. What is a reasonable number of people to follow, anyway? Most users may have a hard time finding 500 accounts they are interested in—while others would think a limit of 10,000 is too low.

Also, people approach Twitter in different ways. Some think you should follow everyone who follows you. Personally, I don’t because that would render Twitter unusable for me. I “only” follow about 700 accounts—less than 5% of the 16,000 who follow me. (Mr. Obama may have time to keep up with 50,000 people, but I’m a busy guy!)

The point is, there is no right or wrong. And there is no perfect formula. We do our best by taking a multi-dimensional approach. We look at a number of factors—including how many people are following you back—before applying limits. We don’t reveal exact limits, because it’s somewhat complicated and, more importantly, if you were to tell spammers exactly what the filtering rules are on your email or, say, Google’s PageRank, they’d just engineer their way around them much more easily.

Making Progress

Like I said, this is still a work in progress. The good news for most people is that we’re taking measures to reduce junk in the system—and it’s working. The bad news for some is that it’s possible you’ll run into a limit and get frustrated. If that happens, please let us know. We want to learn how people want to use Twitter. (Note: We intend to allow you to follow at least as many people as follow you, though there are cases where that might not yet be the case. We will fix that.)

By the way, this is only a small part of our approach to spam in general. We’ll be talking more soon about other measures we’re taking. Thanks for hanging with us as we figure everything out.