Convenience function to run aPPR via rtweet

appr_rtweet(seeds, ...)

Arguments

seeds

Screen names or user IDs of seed nodes in the Twitter graph, as a character vector.

...

Arguments passed on to appr

graph

An abstract_graph() object, such as those created by rtweet_graph() and twittercache_graph(), and igraph::igraph() object. This argument is required.

alpha

Teleportation constant. The teleportation constant is the probability of returning to a seed node at each node transition. alpha must be a valid probabilty; that is, between zero and one. Defaults to 0.15. This is the inverse of the "dampening factor" in the original PageRank paper, so alpha = 0.15 corresponds to a dampening factor of 0.85. Runtime is proportional to 1 / (epsilon * alpha), so small alpha can result in long runtimes.

epsilon

Desired accuracy of approximation. epsilon must be a valid probabilty; that is, between zero and one. Defaults to 1e-6. Runtime is proportional to 1 / (epsilon * alpha), so small epsilon can result in long runtimes.

tau

Regularization term. Additionally inflates the in-degree of each observation by this term by performing the degree adjustment described in Algorithm 3 and Algorithm 4, which are described in vignette("Mathematical details"). Defaults to NULL, in which case tau is set to the average in-degree of the observed nodes. In general, setting it's reasonable to set tau to the average in-degree of the graph.

verbose

Logical indicating whether to report on the algorithms progress. Defaults to TRUE.