Managing network contagion
The present disclosure relates to systems, methods, and computer-readable media for improving the detection, evaluation, and management of computer networks with regard to providing and managing the dispersion of communications. For example, in one or more implementations, a contagion management system can dynamically, efficiently, and quickly identify the extent to which information is expected to disperse in a network based on local and global factors, including virality. In various implementations, the contagion management system can utilize one or more spreading models to determine the potential expected network spread of network information and characteristics as well as can modify network connectivity settings to mitigate network spreading. In this manner, the contagion management system can effectively manage contagions of misinformation, or other characteristics, that spread throughout computer networks.
1 . A computer-implemented method comprising:
identifying a first number of nodes having a target characteristic in a network, the network comprising a plurality of nodes;
generating a global effect factor based on the target characteristic and the network;
determining that a second number of nodes in the network will have the target characteristic at an upcoming period based on the first number of nodes, a network resistance parameter, and the global effect factor; and
based on the second number of nodes satisfying a network threshold at the upcoming period, modifying one or more network connectivity settings by limiting communications from the first number of nodes with the target characteristic to cause a reduction to the second number of nodes in the network that will have the target characteristic in the upcoming period.
2 . The computer-implemented method of claim 1 , wherein the global effect factor indicates a probability that a node in the network not having the target characteristic will have the target characteristic in a next period based on influences of non-directly connected nodes indirectly connected via the network to the node.
3 . The computer-implemented method of claim 1 , wherein modifying the one or more network connectivity settings includes limiting a number of nodes that include the target characteristic to a predetermined number or network percentage for an allotted time.
4 . The computer-implemented method of claim 1 , wherein:
generating the global effect factor comprises generating the global effect factor for a given node in the network that does not have the target characteristic; and
generating the global effect factor comprises generating the global effect factor for a given node in the network that has the target characteristic.
5 . The computer-implemented method of claim 1 , wherein modifying the one or more network connectivity settings includes appending a verification notification to the target characteristic indicating a negative attribute of the target characteristic.
6 . The computer-implemented method of claim 1 , wherein determining that the second number of nodes in the network will have the target characteristic at the upcoming period is based on a depth spreading model and a full-network spreading model.
7 . The computer-implemented method of claim 1 , wherein the network threshold comprises a percentage of nodes in the network that, if satisfied, will cause the target characteristic to spread to throughout the network entirely.
8 . The computer-implemented method of claim 1 , wherein modifying the one or more network connectivity settings comprises reducing cross-global communications between non-neighbor nodes in the network by reducing communications between nodes based on node proximity.
9 . The computer-implemented method of claim 8 , wherein reducing cross-global communications includes restricting communications for nodes with the target characteristic to a network connectivity amount that indicates a number of permitted communication hops between the nodes on non-connected nodes.
10 . The computer-implemented method of claim 1 , further comprising:
generating an attachment parameter for the network by determining an average number of connections between each node of the plurality of nodes and other nodes in the network; and
determining that the second number of nodes in the network will have the target characteristic at the upcoming period utilizing the attachment parameter.
11 . A non-transitory computer-readable storage medium comprising instructions that, when executed by at least one processor, cause a computing device to:
identify a first number of nodes having a target characteristic in a network, the network comprising a plurality of nodes;
generate a global effect factor based on the target characteristic and the network;
determine that a second number of nodes in the network will have the target characteristic at an upcoming period based on the first number of nodes, a network resistance parameter, and the global effect factor; and
based on the second number of nodes satisfying a network threshold at the upcoming period, modifying one or more network connectivity settings by limiting communications from the first number of nodes with the target characteristic to cause a reduction to the second number of nodes in the network that will have the target characteristic in the upcoming period.
12 . The non-transitory computer-readable storage medium of claim 11 , wherein determining that the second number of nodes in the network will have the target characteristic at the upcoming period is based on a depth spreading model or a full-network spreading model.
13 . The non-transitory computer-readable storage medium of claim 12 , wherein the depth spreading model determines an amount of network spreading based on the first number of nodes that have the target characteristic and a given network resistance parameter.
14 . The non-transitory computer-readable storage medium of claim 12 , wherein the full-network spreading model determines a target network resistance parameter needed to spread the target characteristic to all of the plurality of nodes based on the first number of nodes that have the target characteristic and the global effect factor for the target characteristic.
15 . The non-transitory computer-readable storage medium of claim 11 , wherein the network resistance parameter is based on an architecture of the network.
16 . The non-transitory computer-readable storage medium of claim 11 , wherein:
the plurality of nodes comprises each node in the network connected to one or more other nodes of the plurality of nodes; and
the network comprises a social networking system.
17 . A system comprising:
at least one processor; and
a non-transitory computer memory comprising instructions that, when executed by the at least one processor, cause the system to:
identify a first number of nodes having a target characteristic in a network, the network comprising a plurality of nodes;
generate a global effect factor based on the target characteristic and the network;
determine that a second number of nodes in the network will have the target characteristic at an upcoming period based on the first number of nodes, a network resistance parameter, and the global effect factor; and
based on the second number of nodes satisfying a network threshold at the upcoming period, modifying one or more network connectivity settings by limiting communications from the first number of nodes with the target characteristic to cause a reduction to the second number of nodes in the network that will have the target characteristic in the upcoming period.
18 . The system of claim 17 , wherein:
the one or more network connectivity settings indicate which nodes in the network can communicate with corresponding distantly connected nodes;
the second number of nodes comprises a network spreading depth; and
the network threshold comprises all of the plurality of nodes in the network.
19 . The system of claim 17 , wherein modifying the one or more network connectivity settings comprises increasing network resilience based on appending a notification to the target characteristic.
20 . The system of claim 17 , further comprising instructions that, when executed by the at least one processor, cause the system to cause a third number of nodes to have a characteristic opposite to the target characteristic, wherein the third number of nodes is larger than the second number of nodes.