Cascade prediction using behavioral dynmics
AssigneeInternational Business Machines Corporation
InventorsKun Bai, Wei Tan, Fei Wang
Life of this patent
Estimating the term…
Abstract
A system, method and program product for providing cascade prediction. A system is disclosed having: a computing system for receiving observed cascade data, wherein the observed cascade data includes a set of nodes impacted prior to a preliminary time; a sub-cascade processing engine that determines a sub-cascade size of each node in the set of nodes; survival analysis system that utilizes a networked Weibull regression to determine a survival rate of each node in the set of nodes; and a calculation system that applies the survival rate to the sub-cascade size of each node in the set of nodes to generate a predicted cascade size at a future time.
Claims11
A cascade prediction system, comprising:
- a computing system for receiving observed cascade data, wherein the observed cascade data includes a set of nodes impacted prior to a preliminary time;
- a sub-cascade processing engine that determines a sub-cascade size and survival rate of each node in the set of nodes based on node attributes, wherein the node attributes include an average inflow rate of followers of a user, an average republish rate of followers of the user, an inflow rate to the user, an outflow rate of the user, a number of followers to the user, or a number of other users followed by the user;
- survival analysis system that utilizes a networked Weibull regression to determine a survival rate of each node in the set of nodes;
- and
- a calculation system that applies the survival rate to the sub-cascade size of each node in the set of nodes to generate a predicted cascade size at a future time.
A method for predicting cascades, comprising:
- providing a computing system for receiving observed cascade data, wherein the observed cascade data includes a set of nodes impacted prior to a preliminary time;
- determining a sub-cascade size and survival rate of each node in the set of nodes based on node attributes, wherein the node attributes include an average inflow rate of followers of a user, an average republish rate of followers of the user, an inflow rate to the user, an outflow rate of the user, a number of followers to the user, or a number of other users followed by the user;
- utilizing a networked Weibull regression to determine a survival rate of each node in the set of nodes;
- and
- applying the survival rate to the sub-cascade size of each node in the set of nodes to generate a predicted cascade size at a future time.
A computer program product stored on a computer readable storage medium, which when executed by a processor, generates a cascade prediction, the computer program product comprising:
- programming instructions for receiving observed cascade data, wherein the observed cascade data includes a set of nodes impacted prior to a preliminary time;
- programming instructions for determining a sub-cascade size and survival rate of each node in the set of nodes based on node attributes, wherein the node attributes include an average inflow rate of followers of a user, an average republish rate of followers of the user, an inflow rate to the user, an outflow rate of the user, a number of followers to the user, or a number of other users followed by the user;
- programming instructions for utilizing a networked Weibull regression to determine a survival rate of each node in the set of nodes;
- and
- programming instructions for applying the survival rate to the sub-cascade size of each node in the set of nodes to generate a predicted cascade size at a future time.
Dependencies are inferred from the claim text.