Increasing social media presence using machine-learning relevance techniques

Abstract

According to an implementation, a method for digital information retrieval in a social media platform includes transmitting, over a network, information to render a timeline of social content for a user of a client application. The timeline of social content includes messages posted on the messaging platform by user accounts that are connected to a user account of the user in a connection graph. The method includes computing, using a machine-learning algorithm inputted with relevance signals, a relevance level between the user account of the user and a user account not linked to the user account of the user in the connection graph, and transmitting information about a profile of the user to a computing device associated with the user account not linked to the user account of the user in response to the relevance level being greater than a threshold level.

What is claimed is: 
     
         1 . A system comprising:
 at least one processor; and   a non-transitory computer-readable medium storing executable instructions that when executed by the at least one processor cause the at least one processor to:
 select a message posted to a messaging platform by a first user account; 
 compute, using a machine-learning algorithm inputted with relevance signals, a relevance level between content of the message and a second user account, wherein the second user account is not linked to the first user account in a connection graph of the messaging platform, the relevance signals including one or more signals representing the content of the message and one or more signals representing information about the second user account; and 
 in response to the relevance level being greater than a threshold level, transmit a signal to display the message on a computing device associated with the second user account. 
   
     
     
         2 . The system of  claim 1 , wherein the executable instructions include instructions that when executed by the at least one processor cause the at least one processor to:
 determine, using the machine-learning algorithm, a relevant time period of when to display the message; and   transmit the signal to display the message during the relevant time period.   
     
     
         3 . The system of  claim 1 , wherein the executable instructions include instructions that when executed by the at least one processor cause the at least one processor to:
 determine that second user account has viewed content from the first user account;   delay transmission of the signal to display the message for a period of time; and   transmit the signal to display the message in response to an expiration of the period of time.   
     
     
         4 . The system of  claim 1 , wherein the signal is configured to insert the message in a timeline of messages, the timeline of messages including a plurality of messages from user accounts linked to the second user account in the connection graph. 
     
     
         5 . The system of  claim 1 , wherein the machine-learning algorithm is configured to apply weights to the relevance signals to compute the relevance level between the content of the message and the second user account, the machine-learning algorithm configured to periodically update the weights based on actual selections of users. 
     
     
         6 . The system of  claim 1 , wherein the executable instructions include instructions that when executed by the at least one processor cause the at least one processor to:
 select the message by filtering a plurality of messages posted to the messaging platform by the first user account based on an amount of engagements associated with a respective message of the plurality of messages.   
     
     
         7 . The system of  claim 6 , wherein the engagements include at least one of signals of appreciations, comments, or re-shares of a respective message. 
     
     
         8 . The system of  claim 1 , wherein the message posted to the messaging platform by the first user account is selected based on receipt of a user selection from a computing device associated with the first user account. 
     
     
         9 . The system of  claim 1 , wherein the executable instructions include instructions that when executed by the at least one processor cause the at least one processor to:
 compute, using the machine-learning algorithm, a secondary relevance level between a profile of the first user account and a third user account, the third user account not linked to the first user account in the connection graph; and   transmit a secondary signal to display information about the profile to a computing device associated with the third user account.   
     
     
         10 . The system of  claim 1 , wherein the one or more signals representing information about the second user account include at least one of messages that have been engaged with by the second user account, or preferences inferred from the messages that have been engaged with by the second user account. 
     
     
         11 . A method comprising:
 selecting a message posted to a messaging platform by a first user account;   computing, using a machine-learning algorithm inputted with relevance signals, a relevance level between content of the message and a second user account, wherein the second user account is not linked to the first user account in a connection graph of the messaging platform, the relevance signals including one or more signals representing the content of the message and one or more signals representing information about the second user account; and   in response to the relevance level being greater than a threshold level, transmitting a signal to display the message on a computing device associated with the second user account.   
     
     
         12 . The method of  claim 11 , further comprising:
 determining, using the machine-learning algorithm, a relevant time period of when to display the message; and   transmitting the signal to display the message during the relevant time period.   
     
     
         13 . The method of  claim 11 , further comprising:
 determining that second user account has viewed content from the first user account;   delaying transmission of the signal to display the message for a period of time; and   transmitting the signal to display the message in response to an expiration of the period of time.   
     
     
         14 . The method of  claim 11 , further comprising:
 applying weights to the relevance signals to compute the relevance level between the content of the message and the second user account; and   updating the weights based on actual selections of users.   
     
     
         15 . The method of  claim 11 , further comprising:
 selecting the message by filtering a plurality of messages posted to the messaging platform by the first user account.   
     
     
         16 . The method of  claim 15 , wherein the plurality of messages are filtered based on a quality metric associated with a respective message of the plurality of messages. 
     
     
         17 . The method of  claim 15 , wherein the plurality of messages are filtered based on an amount of engagements associated with a respective message of the plurality of messages. 
     
     
         18 . A non-transitory computer-readable medium storing executable instructions that when executed by at least one processor cause the at least one processor to execute operations, the operations comprising:
 selecting a message posted to a messaging platform by a first user account;   computing, using a machine-learning algorithm inputted with relevance signals, a relevance level between content of the message and a second user account, wherein the second user account is not linked to the first user account in a connection graph of the messaging platform, the relevance signals including one or more signals representing the content of the message and one or more signals representing information about the second user account; and   in response to the relevance level being greater than a threshold level, transmitting a signal to display the message on a computing device associated with the second user account.   
     
     
         19 . The non-transitory computer-readable medium of  claim 18 , wherein the operations further comprise:
 computing, using the machine-learning algorithm, a secondary relevance level between a profile of the first user account and a third user account, the third user account not linked to the first user account in the connection graph; and   transmitting a secondary signal to display information about the profile to a computing device associated with the third user account.   
     
     
         20 . The non-transitory computer-readable medium of  claim 18 , wherein the operations further comprise:
 applying weights to the relevance signals to compute the relevance level between the content of the message and the second user account; and   updating the weights based on actual selections of users.   
     
     
         21 . The non-transitory computer-readable medium of  claim 18 , wherein the operations further comprise:
 determining that second user account has viewed content from the first user account;   delaying transmission of the signal to display the message for a period of time; and   transmitting the signal to display the message in response to an expiration of the period of time.