Subscribe to DSC Newsletter

Here are a few ideas to catch spam:

  • Create decoy profiles to monitor large-scale spam activity. Ban members who send spam to these profiles.
  • Monitor more closely accounts from members that have no information on their profile.
  • When a new member signs up, in addition to the traditional questions (experience, fields of expertize), add one question such as "what is the result of (49-15)x(59+945)/(9+8)". Monitor more closely members who provide the wrong answer.
  • Monitor more closely brand new members with blank profiles, or brand new members with irrelevant / spammy links on their profile (better: delete these accounts).
  • Members should not accept friend requests from other unknown members with a blank profile. Also they are encouraged to report spam issues: spammers, once detected, are terminated and this in turn clears the spam message on everyone's profile.
  • Non members are not allowed to post message.

Views: 63

Replies to This Discussion

How many decoy profiles do you need to capture 95% of the spam? Is there a rule of thumb, e.g. with 6000 members, you need 20 decoy profiles in your honey pot, to catch most of the spam?

RSS

On Data Science Central

© 2019   AnalyticBridge.com is a subsidiary and dedicated channel of Data Science Central LLC   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service