SYSTEM AND METHOD FOR CLASSIFYING A CONTAGIOUS PHENOMENON PROPAGATING ON A NETWORK
This disclosure concerns systems and methods for classifying at least one contagious phenomenon propagating on a network. Classifying may be based on one or more of a peakedness, a commitment, a commitment by subsequent uses, a commitment by time range, and a dispersion related to engagement with the contagious phenomenon.
1 . A method, comprising:
classifying at least one contagious phenomenon propagating on a network,
wherein classifying is based on one or more of a peakedness, a commitment, a commitment by subsequent uses, a commitment by time range, and a dispersion related to engagement with the contagious phenomenon.
2 . The method of claim 1 , wherein the peakedness of the contagious phenomenon is a measure of how concentrated that phenomenon is in time and is determined by calculating the fraction of all engagements with that phenomenon that occur on the day with the most engagements with that phenomenon.
3 . The method of claim 1 , wherein commitment is the measure of the average scope of engagement with a contagious phenomenon by nodes in the network.
4 . The method of claim 1 , wherein commitment by subsequent uses is the average number of subsequent engagements with the contagious phenomenon after a node of the network's first engagement.
5 . The method of claim 1 , wherein commitment by time range is the average time period between the first and last engagement with the phenomenon by a node in the network measured over a time window.
6 . The method of claim 1 , wherein dispersion is a measure of the distribution of engagements with the contagious phenomenon over the network through which it propagates.
7 . The method of claim 6 , wherein measuring the distribution of engagements with a phenomenon over a network includes measuring one or more of a normalized concentration and a cohesion.
8 . The method of claim 7 , wherein the normalized concentration of the contagious phenomenon presupposes a partition of the underlying network into discrete clusters.
9 . The method of claim 8 , wherein the normalized concentration of the contagious phenomenon is the fraction of all engagements that come from the cluster that engages most with the phenomenon.
10 . The method of claim 7 , wherein the cohesion of the contagious phenomenon is a network density of a subgraph of all nodes engaging with the phenomenon.
11 . The method of claim 10 , wherein the network density of a graph is the total number of connections between nodes in the graph divided by the total possible number of connections.
12 . The method of claim 11 , wherein the formula for calculating the total possible number of connections is (number of nodes*(number of nodes−1)/2).
13 . The method of claim 1 , wherein engagement includes one or more of a mention, a re-tweet, a hashtag, a link, a post, and a check-in.
14 . A method of visualizing a chronotope, comprising:
selecting a contagious phenomenon propagating through a network;
binning the set of engagements of network users with the contagious phenomenon by a time period;
partitioning the volume of engagements for each time period by a plurality of groups of network users;
generating a grid where columns correspond to groups of network users and rows correspond to days; and
populating each cell of the grid uniquely in correspondence with one of the plurality of groups of network users to represent an aspect of the volume of engagements.
15 . The method of claim 14 , wherein when a color is used in populating, a cue as to the volume of engagements with the contagious phenomenon during that time period for that group of network users is given via the brightness of the color.