Efficient dynamic centrality metrics for election advertising - a case study

In prior work [1], we have shown how advertising channels should be chosen by a budget-constrained electoral campaign. In this poster, we apply the resulting proposed algorithm to the MIT Social Evolution [2] data-set (N=84), which captured political discussions, inclinations, and voting behaviors around the 2008 US Presidential Election within a student dorm. We compare the resulting centrality metrics developed from our algorithm (which have a direct mapping to optimal channel choice decisions) against more traditional static centralities, and show how employing them leads to more votes.

[1] Eshghi, S., Preciado, V.M., Sarkar, S., Venkatesh, S.S., Zhao, Q., D'Souza, R. and Swami, A., 2017. Spread, then Target, and Advertise in Waves: Optimal Capital Allocation Across Advertising Channels. arXiv preprint arXiv:1702.03432.

[2] A. Madan, M. Cebrian, S. Moturu, K. Farrahi, A. Pentland, Sensing the 'Health State' of a Community, Pervasive Computing, Vol. 11, No. 4, pp. 36-45 Oct 2012