***** To join INSNA, visit http://www.insna.org *****
Great point. I have discussed this explicitly with several people
including Ron Burt who incidentally made the same observation. While it
is true that structural equivalence could be another factor in the
adoption of new practices (the literature on this point is long),
measuring structural equivalence without bias using incomplete data on
network structure is non-trivial to say the least. Regardless of whether
you are after structural equivalence, regular equivalence or automorphic
equivalence, the constraints on your capacity to measure these factors
in a 30 million node sample of an ~ 150-200 million node network are
significant. In addition, from the perspective of optimal promotion or
containment policies (in a peer to peer diffusion sense - i.e. one node
directly influences another) we decided to focus on the importance of
transmission through connections. For these reasons, we came at this
from a more "relational" perspective. But, your point is well taken...
How could we in future work incorporate structural equivalence? (I have
a tabled discussion with Ron on this exact point on the back burner, so
any additional input and ideas here are much appreciated).
Assistant Professor, NYU Stern School of Business.
Research Affiliate, MIT Sloan School of Management.
Personal Webpage: http://pages.stern.nyu.edu/~saral
SSRN Page: http://ssrn.com/author=110270
WIN Workshop: http://www.winworkshop.net
Blyden Potts wrote:
> In addition to (1) peer influence or social contagion and (2) homophily,
> isn't there also a rather substantial factor of (3) structural equivalence,
> separate from either peer influence or homophily, to consider as a factor in
> the adoption of new practices?
> Blyden Potts
> -----Original Message-----
> From: Social Networks Discussion Forum [mailto:[log in to unmask]] On
> Behalf Of Sinan Aral
> Sent: Tuesday, January 26, 2010 5:17 PM
> To: [log in to unmask]
> Subject: Distinguishing Influence and Homophily
> ***** To join INSNA, visit http://www.insna.org *****
> Dear All,
> Several on this list may be interesting in this paper we just published in
> PNAS. It develops a method for distinguishing peer influence from homophily
> in large dynamic networks. We apply it to 27 million users of
> Yahoo's instant messaging graph to predict influence in the adoption of a
> new mobile service application. Enjoy:)
> "Distinguishing Influence Based Contagion from Homophily Driven Diffusion in
> Dynamic Networks"
> Node characteristics and behaviors are often correlated with the structure
> of social networks over time. While evidence of this type of assortative
> mixing and temporal clustering of behaviors among linked nodes is used to
> support claims of peer influence and social contagion in networks, homophily
> may also explain such evidence.
> Here we develop a dynamic matched sample estimation framework to distinguish
> influence and homophily effects in dynamic networks, and we apply this
> framework to a global instant messaging network of 27.4 million users, using
> data on the day-by-day adoption of a mobile service application and users'
> longitudinal behavioral, demographic, and geographic data.
> We find that previous methods overestimate peer influence in product
> adoption decisions in this network by 300-700%,
> and that homophily explains 50% of the perceived behavioral contagion. These
> findings and methods are essential to both our understanding of the
> mechanisms that drive contagions in networks and our knowledge of how to
> propagate or combat them in domains as diverse as epidemiology, marketing,
> development economics, and public health.
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.