The users of microblogging services, such as Twitter, use the count of followers
of an account as a measure of its reputation or influence. For those unwilling or unable to
attract followers naturally, a growing industry of “Twitter follower markets” provides followers
for sale. Some markets use fake accounts to boost the follower count of their customers,
while others rely on a pyramid scheme to turn non-paying customers into followers for each
other, and into followers for paying customers. In this paper, we present a detailed study of Twitter Followers Markets, and we show that it is possible to detect users that purchased followers on Twitter.
Follow the Green: Growth and Dynamics on Twitter Follower Markets
1. Follow the Green:
Growth and Dynamics in
Twitter Follower Markets
Gianluca Stringhini, Gang Wang, Manuel Egele*, Christopher
Kruegel, Giovanni Vigna, Ben Y. Zhao, Haitao Zheng
UC Santa Barbara
*Carnegie Mellon University
2. Twitter Followers = Perceived Reputation
Services that measure the
Twitter influence of an
account (such as Klout) take
the number of followers into
account, together with a
number of other indicators
Building a network of followers is difficult!
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
2
4. Can One Really Buy Followers?
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
4
5. Twitter Follower Markets
Different types of followers for sale
• Fake accounts (Sybils)
• Compromised accounts
• Pyramid schemes
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
5
6. Pyramid Markets
Free Subscriber
Paid Subscriber
• Free subscribers → Victims
• Paid subscribers → Customers
Twitter’s ToS forbids users to participate in Twitter Follower Markets
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
6
7. Our Contributions
• We study the Twitter Follower Market phenomenon
• We analyze the characteristics of market customers and victims
• We can detect accounts that bought followers
Twitter could block such accounts
Twitter Follower Markets would go bankrupt
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
7
8. Outline of the Talk
• Collection of Twitter Follower Market Data
• Characteristics of Victims and Customers
• Detecting Market Customers
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
8
9. Outline of the Talk
• Collection of Twitter Follower Market Data
• Characteristics of Victims and Customers
• Detecting Market Customers
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
9
10. Active Twitter Follower Markets
Market (sorted by
order of returned
results)
Different price, depending on the type of
followers sold: real followers are more
expensive
Newfollow.info
$216
YES
Bigfolo.com
$91.99
YES
Bigfollow.net
$70
YES
Intertwitter.com
$65
NO (fake accounts)
Justfollowers.in
$95
YES
Twiends.com
$169
NO (fake accounts)
$49
NO (fake accounts)
Devumi.com
$64
NO (fake accounts)
Hitfollow.info
$214
YES
Plusfollower.info
$214
YES
Buyactivefans.com
• We queried search engines looking for
Twitter Follower Markets
• We developed a classifier to determine
whether a website is actually selling
followers
Pyramid?
Socialwombat.com
We studied the top-five
ranked markets
$ for 10K Followers
$40
NO (fake accounts)
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
10
11. Market Sizes
We look at tweets advertising the top five markets
10% of the all public tweets (3.3 billion tweets), collected over a
period of four months
Market
Tweets
Victims
BigFollow
662,858
90,083
BigFolo
4,732,016
611,825
JustFollowers
302
257
NewFollow
77,865
38,341
InterTwitter
0
0
Total
5,473,041
740,506
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
11
12. Detecting Market Victims
We purchased followers from the most popular five markets
Whoever followed us is
a victim
In total, we identified 69,222 victims
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
12
13. Detecting Market Customers
Get more
followers!
Get more
followers!
Get more
followers!
Get more
followers!
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
13
14. Detecting Market Customers
We signed up 180 newly-created accounts as market victims
We identified 2,909 market customers
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
14
15. Outline of the Talk
• Collection of Twitter Follower Market Data
• Characteristics of Victims and Customers
• Detecting Market Customers
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
15
16. Customer Characteristics
We compared our set of customers to a set of two
million regular users picked at random
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
16
17. Customer Follower Dynamics
Inflation period
Deflation period
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
17
18. Customer Follower Dynamics
During an observation period of one week:
• Spike in Followers ≥ 50 over an hour:
50% Customers, 0.4% Regular
• Steady decrease of followers for ≥ 10 consecutive hours:
60% Customers, 0.05% Regular
• Change of number of followers ≈ 0:
0% Customers, 30% Regular
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
18
19. Victim Characteristics
Different strategies for operating markets
• Some markets form dense cliques of victims
• Some market’s victims follow many customers
Common characteristics of victim accounts:
• Victims follow each other
• A small fraction of victim accounts (≈20%) gets suspended
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
19
20. Outline of the Talk
• Collection of Twitter Follower Market Data
• Characteristics of Victims and Customers
• Detecting Market Customers
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
20
21. Follower Dynamics Detection
We developed a classifier to detect customers in the wild
Three types of features (calculated over a week)
•Increase features (1,000 features)
Number of times spike of d followers during an hour
•Decrease features (168 features)
Number of times steady decrease of followers for d consecutive hours
•Stationary features (168 features)
Number of times followers remained constant for d consecutive hours
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
21
22. Follower Dynamics Detection
Ground truth: Set of 2,909 customers and 10,000 regular
accounts (monitored for a week)
Classifier: Support Vector Machines
10-fold cross validation: 98.4% true positive rate
0.02% false positive rate
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
22
23. Detecting Customers in the Wild
We monitored our set of two million regular accounts for two weeks
We detected 684 customers
•Observed only two million accounts
•Purchase needs to happen during our observation
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
23
24. Analysis of the Identified Customers
The detected accounts have the expected characteristics of customers
•They belong to wanna-be celebrities and small businesses
•They do not post interesting content
Buying followers does not help in becoming influential (median Klout 45)
• A customer with 103,000 followers → same Klout score as me (57)
Twitter fails in detecting customers: 2 out of 684 were suspended
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
24
25. Discussion
Our proposed approach to detect and block market customers
could undermine the foundations of Twitter Account Markets
Market operators could adapt, and try to evade detection
•Provide followers slowly
•Have no control over the unfollow behavior!
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
25
26. Conclusions
• We performed a large-scale study of Twitter Follower Markets
• We propose techniques to detect market customers
• We advocate for Twitter to adopt similar techniques
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
26
28. Problem: the Dynamic
Classifier is Demanding
In the paper, we propose two alternative methods:
•A static filter, to discard as many candidates as
possible
•A static classifier, that uses static profile information
to detect customers
System
TP rate
FP rate
Static Filter
93.7%
63%
Static Classifier
91%
3.3%
Dynamic Classifier
98.4%
0.02%
Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets
28