Adverse user behavior detection and mitigation
Aspects of the present disclosure relate to adverse user behavior detection and mitigation. In examples, a user account of a social platform may be trusted or untrusted. If the user account is untrusted, activity of the user account may be buffered so as to not directly affect social metrics of the social platform. For example, if the untrusted user account follows a target user account, the untrusted user account may be added to a separate set of followers or otherwise separated from a set of trusted followers of the target user account. Eventually, each user account in the separate set is evaluated to determine whether the user account has transitioned to a trusted user. If the user account is now trusted, it may be migrated to the set of trusted followers. However, if the user account is untrusted, it may be removed from the separate set, thereby reverting the activity.
1. A system comprising:
at least one processor; and
memory storing instructions that, when executed by the at least one processor, causes the system to perform a set of operations, the set of operations comprising:
receiving a request to follow a target user account of a social platform, wherein the request is associated with a requesting user account;
evaluating a trust metric associated with the requesting user account based on a threshold to determine whether the requesting user account is a trusted user account of the social platform, wherein the trust metric corresponds to a set of signals associated with the requesting user account;
when it is determined that the requesting user account is a trusted user account, adding the requesting user account to a set of followers of the target user account; and
when it is determined that the requesting user account is not a trusted user account, updating a buffer data structure based on the request to follow the target user account, wherein the buffer data structure is different than the set of followers of the target user account, thereby buffering the request to follow the target user account.
2. The system of claim 1 , wherein the set of operations further comprises:
generating a social metric associated with the target user account based at least in part on the set of followers of the trusted user account and the buffer data structure associated with the target user account; and
providing the generated social metric associated with the target user account.
3. The system of claim 1 , wherein updating the buffer data structure comprises:
determining whether the buffer data structure associated with the target user account exceeds a predetermined threshold; and
when it is determined that the buffer data structure exceeds the predetermined threshold:
processing each user account associated with the buffer data structure to generate a set of trusted user accounts; and
adding each user account of the set of trusted user accounts to the set of followers of the target user account.
4. The system of claim 3 , wherein processing each user account to generate the set of trusted user accounts comprises:
determining whether each user account associated with the buffer data structure is a trusted user account of the social platform based at least in part on an associated set of user activity signals.
5. The system of claim 3 , wherein updating the buffer data structure further comprises:
when it is determined that the buffer data structure exceeds the predetermined threshold:
removing each user account from the buffer data structure that is not in the set of trusted user accounts.
6. The system of claim 3 , wherein the predetermined threshold is programmatically determined based at least in part on a social metric associated with the target user account.
7. The system of claim 3 , wherein:
the requesting user account is in the generated set of trusted user accounts; and
the requesting user account is added to the set of followers of the target user account.
8. A method of processing a request to follow a target user of a social platform, comprising:
receiving, from a client device associated with a requesting user account, a request to follow the target user account of a social platform;
evaluating a trust metric associated with the requesting user account based on a threshold to determine whether the requesting user account is a trusted user account of the social platform, wherein the trust metric corresponds to a set of user signals associated with the requesting user account; and
based on determining that the requesting user account is not a trusted user account, updating a buffer data structure based on the request to follow the target user account, wherein the buffer data structure is different than the set of followers of the target user account, thereby buffering the request to follow the target user account.
9. The method of claim 8 , further comprising:
generating a social metric associated with the target user account based at least in part on the buffer data structure associated with the target user account; and
providing, to the client device, the generated social metric associated with the target user account.
10. The method of claim 8 , wherein updating the buffer data structure comprises:
determining whether the buffer data structure associated with the target user account exceeds a predetermined threshold; and
based on determining that the buffer data structure exceeds the predetermined threshold:
processing each user account associated with the buffer data structure to generate a set of trusted user accounts; and
adding each user account of the set of trusted user accounts to the set of followers of the target user account.
11. The method of claim 10 , wherein processing each user account to generate the set of trusted user accounts comprises:
determining whether each user account associated with the buffer data structure is a trusted user account of the social platform based at least in part on an associated set of user signals.
12. The method of claim 10 , wherein updating the buffer data structure further comprises:
based on determining that the buffer data structure exceeds the predetermined threshold:
removing each user account from the buffer data structure that is not in the set of trusted user accounts.
13. The method of claim 10 , wherein:
the requesting user account is in the generated set of trusted user accounts; and
the requesting user account is added to the set of followers of the target user account.