Content virality determination and visualization

Abstract

Various techniques of content virality determination and visualization are disclosed herein. For example, a method of determining network content virality metric includes constructing a diffusion cascade for a computer network content based on a plurality of time points at which individual users adopt the network content and connection information of the users. The method also includes calculating, with a processor, a virality metric of the network content based on a structural characteristic of the constructed diffusion cascade. Based on the calculated virality metric, one may determine if the network content is viral.

I/we claim: 
     
         1 . A method of determining content virality in a computer network having a plurality of interconnected client devices associated with corresponding users, comprising:
 receiving network data having a plurality of time points at which individual users interact with a network content item via the computer network and connection information regarding one or more social network relationships among the individual users over the computer network;   inferring propagation of the network content item from one user to another based on the plurality of time points and the connection information, wherein inferring propagation includes designating a plurality of parent-child node relationships for each pair of the individual users to derive a diffusion cascade, wherein one user is designated as a parent node and another user designated as a child node when the users are connected and a time point corresponding to the user occurs earlier than another time point corresponding to the another user;   calculating a virality metric of the network content item based on the derived diffusion cascade; and   transmitting recommendations of the network content item to additional users via the computer network when the calculated virality metric is above a threshold value.   
     
     
         2 . The method of  claim 1  wherein the diffusion cascade having a plurality of nodes representing the users, the nodes being arranged based on the time points at which the individual users adopt the network content item. 
     
     
         3 . The method of  claim 1  wherein inferring propagation includes:
 determining one of the users with an earliest time point; and 
 inferring that the other users adopt the network content item from the one of the users. 
 
     
     
         4 . The method of  claim 1  wherein inferring propagation includes:
 determining one of the users with an earliest time point; 
 designating the determined one of the users as a root node; 
 inferring that the other users adopt the network content from the one of the users; and 
 designating the other users as child nodes of the root node. 
 
     
     
         5 . The method of  claim 1  wherein inferring propagation includes:
 determining whether the time point is earlier than the another time point; and 
 in response to determining that the time point is earlier than the another time point, inferring that the another user adopts the network content item from the user. 
 
     
     
         6 . The method of  claim 1  wherein inferring propagation includes:
 determining whether the time point is earlier than the another time point; 
 in response to determining that the time point is earlier than the another time point, 
 designating the user as a parent node and inferring that the another user adopts the network content item from the user; and 
 designating the another user as child node of the parent node. 
 
     
     
         7 . The method of  claim 1  wherein designating the plurality of parent-child node relationship includes:
 comparing the time point to of the another time point; 
 determining whether the time point corresponds to the user connected to the another user corresponding to the another time point; 
 in response to determining that the time point is earlier than the another time point and the user is connected to the another user, 
 designating the user as a parent node and the another user as a child node; and 
 repeating the comparing, determining, and designating operations until all of the time points are processed to derive the diffusion cascade. 
 
     
     
         8 . The method of  claim 7  wherein calculating the virality metric includes calculating the virality metric also based on at least one of:
 an average distance between all pairs of the nodes in the diffusion cascade, the distance between a pair of nodes being a distance of shortest path between the pair of nodes; 
 a probability that two random nodes have a distinct parent node in the diffusion cascade; or 
 an average depth of the nodes in the diffusion cascade. 
 
     
     
         9 . The method of  claim 7 , further comprising displaying the derived diffusion cascade in a static or time lapsed manner. 
     
     
         10 . The method of  claim 7 , further comprising:
 displaying the derived diffusion cascade with child nodes of a particular parent node highlighted; or   displaying the derived diffusion cascade with a highlighted path from one of the nodes to all other connected nodes.   
     
     
         11 . The method of  claim 1 , further comprising identifying trending network content items and/or corresponding users based on the calculated virality metric of the network content items. 
     
     
         12 . A computing system, comprising:
 a processor; and   a memory containing instructions executable by the processor to cause the processor to perform a process including:
 receiving, with the processor, network data having a plurality of time points at which individual users interact with a network content item in a computerized social network and connection information of the users in the computerized social network; 
 successively designating a plurality of parent-child node relationships for each pair of the individual users to derive a diffusion cascade, wherein a first user is assigned as a parent node and a respective second user assigned as a child node when a first time point of the plurality of time points corresponding to the first user occurs earlier than a respective second time point corresponding to the second user and the connection information indicates that the first and second users are connected; 
 calculating, with the processor, a virality metric of the network content item based on the derived diffusion cascade; and 
 transmitting messages to additional users via the computerized social network to recommend of the network content item when the calculated virality metric exceeds a threshold value. 
   
     
     
         13 . The computing system of  claim 12  wherein the diffusion cascade include a plurality of nodes representing the users, the nodes being arranged based on the time points at which the individual users adopt the network content item. 
     
     
         14 . The computing system of  claim 12  wherein successively designating further comprises:
 determining that one of the users has an earliest time point; and 
 inferring that the other users adopt the network content item from the one of the users. 
 
     
     
         15 . The computing system of  claim 12  wherein successively designating further comprises:
 determining that one of the users has an earliest time point; 
 designating the determined one of the users as a root node; 
 inferring that the other users adopt the network content from the one of the users; and 
 designating the other users as child nodes of the root node. 
 
     
     
         16 . The computing system of  claim 12  wherein calculating the virality metric of the network content includes calculating the virality metric also based on at least one of:
 an average distance between all pairs of the nodes in the diffusion cascade, the distance between a pair of nodes being a distance of shortest path between the pair of nodes; 
 a probability that two random nodes have a distinct parent node in the diffusion cascade; or 
 an average depth of the nodes in the diffusion cascade. 
 
     
     
         17 . A computer readable storage device containing instructions executable by the processor to cause a processor to perform a process including:
 receiving, from a server in a computerized social network, network data having a plurality of time points at which individual users interact with a network content item in the computerized social network and connection information of the users in the computerized social network;   repetitively designating a plurality of parent-child node relationships for each pair of the individual users to derive a diffusion cascade, wherein a first user is assigned as a parent node and a respective second user assigned as a child node when a first time point of the plurality of time points corresponding to the first user occurs earlier than a respective second time point corresponding to the second user and the connection information indicates that the first and second users are connected;   calculating a virality metric of the network content item based on the derived diffusion cascade; and   transmitting, via the computerized social network, messages to additional users to recommend of the network content item when the calculated virality metric exceeds a threshold value.   
     
     
         18 . The computer readable storage device of  claim 17  wherein repetitively designating further comprises:
 determining that one of the users has an earliest time point; and 
 inferring that the other users adopt the network content item from the one of the users. 
 
     
     
         19 . The computer readable storage device of  claim 17  wherein repetitively designating further comprises:
 determining that one of the users has an earliest time point; 
 designating the determined one of the users as a root node; 
 inferring that the other users adopt the network content from the one of the users; and 
 designating the other users as child nodes of the root node. 
 
     
     
         20 . The computer readable storage device of  claim 17  wherein calculating the virality metric of the network content includes calculating the virality metric also based on at least one of:
 an average distance between all pairs of the nodes in the diffusion cascade, the distance between a pair of nodes being a distance of shortest path between the pair of nodes; 
 a probability that two random nodes have a distinct parent node in the diffusion cascade; or 
 an average depth of the nodes in the diffusion cascade.