Follow the Green:
Growth and Dynamics in
Twitter Follower Markets
Gianluca Stringhini, Gang Wang, Manuel Egele*, Christoph...
Twitter Followers = Perceived Reputation

Services that measure the
Twitter influence of an
account (such as Klout) take
t...
Shortcuts to Success

Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets

3
Can One Really Buy Followers?

Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets

4
Twitter Follower Markets
Different types of followers for sale
• Fake accounts (Sybils)
• Compromised accounts
• Pyramid s...
Pyramid Markets

Free Subscriber
Paid Subscriber

• Free subscribers → Victims
• Paid subscribers → Customers
Twitter’s To...
Our Contributions

• We study the Twitter Follower Market phenomenon
• We analyze the characteristics of market customers ...
Outline of the Talk
• Collection of Twitter Follower Market Data
• Characteristics of Victims and Customers
• Detecting Ma...
Outline of the Talk
• Collection of Twitter Follower Market Data
• Characteristics of Victims and Customers
• Detecting Ma...
Active Twitter Follower Markets
Market (sorted by
order of returned
results)

Different price, depending on the type of
fo...
Market Sizes
We look at tweets advertising the top five markets
10% of the all public tweets (3.3 billion tweets), collect...
Detecting Market Victims
We purchased followers from the most popular five markets

Whoever followed us is
a victim

In to...
Detecting Market Customers
Get more
followers!

Get more
followers!

Get more
followers!

Get more
followers!

Gianluca St...
Detecting Market Customers
We signed up 180 newly-created accounts as market victims

We identified 2,909 market customers...
Outline of the Talk
• Collection of Twitter Follower Market Data
• Characteristics of Victims and Customers
• Detecting Ma...
Customer Characteristics
We compared our set of customers to a set of two
million regular users picked at random

Gianluca...
Customer Follower Dynamics

Inflation period

Deflation period

Gianluca Stringhini – Follow the Green: Growth and Dynamic...
Customer Follower Dynamics
During an observation period of one week:
• Spike in Followers ≥ 50 over an hour:
50% Customers...
Victim Characteristics
Different strategies for operating markets
• Some markets form dense cliques of victims
• Some mark...
Outline of the Talk
• Collection of Twitter Follower Market Data
• Characteristics of Victims and Customers
• Detecting Ma...
Follower Dynamics Detection
We developed a classifier to detect customers in the wild
Three types of features (calculated ...
Follower Dynamics Detection
Ground truth: Set of 2,909 customers and 10,000 regular
accounts (monitored for a week)
Classi...
Detecting Customers in the Wild

We monitored our set of two million regular accounts for two weeks

We detected 684 custo...
Analysis of the Identified Customers
The detected accounts have the expected characteristics of customers
•They belong to ...
Discussion
Our proposed approach to detect and block market customers
could undermine the foundations of Twitter Account M...
Conclusions

• We performed a large-scale study of Twitter Follower Markets
• We propose techniques to detect market custo...
Questions?
gianluca@cs.ucsb.edu
@gianlucaSB

Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follow...
Problem: the Dynamic
Classifier is Demanding
In the paper, we propose two alternative methods:
•A static filter, to discar...
Upcoming SlideShare
Loading in …5
×

Follow the Green: Growth and Dynamics on Twitter Follower Markets

633 views

Published on

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.

Published in: Social Media, Technology
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
633
On SlideShare
0
From Embeds
0
Number of Embeds
12
Actions
Shares
0
Downloads
37
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

Follow the Green: Growth and Dynamics on Twitter Follower Markets

  1. 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. 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
  3. 3. Shortcuts to Success Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets 3
  4. 4. Can One Really Buy Followers? Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets 4
  5. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 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. 17. Customer Follower Dynamics Inflation period Deflation period Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets 17
  18. 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. 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. 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. 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. 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. 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. 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. 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. 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
  27. 27. Questions? gianluca@cs.ucsb.edu @gianlucaSB Gianluca Stringhini – Follow the Green: Growth and Dynamics in Twitter Follower Markets 27
  28. 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

×