Active players in a network tell the story: Parsimony in modeling huge networks

Amit Rechavi, Sheizaf Rafaeli, Transforming the Curriculum: South African Imperatives and 21st Century, Aug 12, 2014
Commentary by Stephen Downes

One problem with studying networks is the huge amount of data generated. But what if you just studied the active members of a network, thus reducing significanty the data that hs to be crunched? Would it be reliable? In some cases, yes. "The partial network has several basic topological parameters that correlate with activity parameters of the entire social network and, hence, make it suitable for depicting the dynamic parameters of the huge network." There's a risk, though. By definition, for example, dropouts would no longer be counted in, say, MOOC statistics, effectively eliminating dropout rates as a measure. But then again, that might not be a bad thing.

Views: 0 today, 146 total (since January 1, 2017).[Direct Link]