Bot resistant network service communications

Abstract

Systems and methods for subscription-based product referrals are provided. In example embodiments, a user request to refer a subscription is received. A user selection of a social network connection having a social network relationship with the user on a social network service is received. A referral request is transmitted to a device of the social network connection. Acceptance of the referral request is determined. Based on determining acceptance of the referral request, a credit is provided to the user.

That which is claimed: 
     
         1 . A method comprising:
 accessing performance metrics associated with a network site user, the network site user having a network site account on a network site;   determining, based on the performance metrics associated with the network site user, a quality score for the network site user, wherein the quality score indicates that a likelihood that the network site user is a bot is greater than a first threshold;   modifying an account setting of the network site account of the network site user; and   subsequent to modifying the account setting of the network site account of the network site user, displaying a network site message associated with the network site user on a graphical user interface, wherein displaying the network site message comprises causing a warning to be displayed proximate the network site message on the graphical user interface.   
     
     
         2 . The method of  claim 1 , wherein the warning indicates that the network site user is a bot based at least in part on the determination that the likelihood that the referral network site user is a bot is greater than the first threshold. 
     
     
         3 . The method of  claim 1 , wherein displaying the network site message associated with the network site user comprises deemphasizing the network site message based at least in part on the determination that the likelihood that the referral network site user is a bot is greater than the first threshold. 
     
     
         4 . The method of  claim 3 , wherein deemphasizing the network site message comprises reducing a visual emphasis associated with the network site message. 
     
     
         5 . The method of  claim 1 , further comprising:
 generating the performance metrics, wherein generating the performance metrics comprises:
 determining a ratio of a first quantity of previous network site messages associated with the network site user that are associated with an interaction to a second quantity of previous network site messages associated with the network site user displayed on the graphical user interface; and 
 determining that the ratio is lower than a pre-configured threshold. 
   
     
     
         6 . The method of  claim 1 , wherein, subsequent to displaying the network site message associated with the network site user on the graphical user interface, suspending access to the network site for the network site user. 
     
     
         7 . The method of  claim 1 , wherein, subsequent to displaying the network site message associated with the network site user on the graphical user interface, banning the network site user from the network site. 
     
     
         8 . A system comprising:
 a processor, and a memory including instructions, which when executed by the processor, cause the processor to perform operations comprising:   accessing performance metrics associated with a network site user, the network site user having a network site account on a network site;   determining, based on the performance metrics associated with the network site user, a quality score for the network site user, wherein the quality score indicates that a likelihood that the network site user is a bot is greater than a first threshold;   modifying an account setting of the network site account of the network site user; and   subsequent to modifying the account setting of the network site account of the network site user, displaying a network site message associated with the network site user on a graphical user interface, wherein displaying the network site message comprises causing a warning to be displayed proximate the network site message on the graphical user interface.   
     
     
         9 . The system of  claim 8 , wherein the warning indicates that the network site user is a bot based at least in part on the determination that the likelihood that the referral network site user is a bot is greater than the first threshold. 
     
     
         10 . The system of  claim 8 , wherein displaying the network site message associated with the network site user comprises deemphasizing the network site message based at least in part on the determination that the likelihood that the referral network site user is a bot is greater than the first threshold. 
     
     
         11 . The system of  claim 10 , wherein deemphasizing the network site message comprises reducing a visual emphasis associated with the network site message. 
     
     
         12 . The system of  claim 8 , wherein the processor is further caused to perform operations comprising:
 generating the performance metrics, wherein generating the performance metrics comprises:
 determining a ratio of a first quantity of previous network site messages associated with the network site user that are associated with an interaction to a second quantity of previous network site messages associated with the network site user displayed on the graphical user interface; and 
 determining that the ratio is lower than a pre-configured threshold. 
   
     
     
         13 . The system of  claim 8 , wherein, subsequent to displaying the network site message associated with the network site user on the graphical user interface, suspending access to the network site for the network site user. 
     
     
         14 . The system of  claim 8 , wherein, subsequent to displaying the network site message associated with the network site user on the graphical user interface, banning the network site user from the network site. 
     
     
         15 . A non-transitory machine-readable medium storing instructions that, when executed by at least one processor of a machine, cause the machine to perform operations comprising:
 accessing performance metrics associated with a network site user, the network site user having a network site account on a network site;   determining, based on the performance metrics associated with the network site user, a quality score for the network site user, wherein the quality score indicates that a likelihood that the network site user is a bot is greater than a first threshold;   modifying an account setting of the network site account of the network site user; and   subsequent to modifying the account setting of the network site account of the network site user, displaying a network site message associated with the network site user on a graphical user interface, wherein displaying the network site message comprises causing a warning to be displayed proximate the network site message on the graphical user interface.   
     
     
         16 . The non-transitory machine-readable medium of  claim 15 , wherein the warning indicates that the network site user is a bot based at least in part on the determination that the likelihood that the referral network site user is a bot is greater than the first threshold. 
     
     
         17 . The non-transitory machine-readable medium of  claim 15 , wherein displaying the network site message associated with the network site user comprises deemphasizing the network site message based at least in part on the determination that the likelihood that the referral network site user is a bot is greater than the first threshold. 
     
     
         18 . The non-transitory machine-readable medium of  claim 17 , wherein deemphasizing the network site message comprises reducing a visual emphasis associated with the network site message. 
     
     
         19 . The non-transitory machine-readable medium of  claim 15 , wherein the machine is further caused to perform operations comprising:
 generating the performance metrics, wherein generating the performance metrics comprises:
 determining a ratio of a first quantity of previous network site messages associated with the network site user that are associated with an interaction to a second quantity of previous network site messages associated with the network site user displayed on the graphical user interface; and 
 determining that the ratio is lower than a pre-configured threshold. 
   
     
     
         20 . The non-transitory machine-readable medium of  claim 15 , wherein, subsequent to displaying the network site message associated with the network site user on the graphical user interface, suspending access to the network site for the network site user.