The last few years have seen signifi cant investment in social media as an adver sing, marke ng and customer outreach opportunity. In the US alone, in 2010, almost $ 1.7 bn was spent by adver sers on social media marke ng, with 53 per cent specifi cally allocated to Facebook 1 . Due to the explicit links that users maintain with each other, social media pla orms are perceived as a highly suited environment for network-based marke ng: word-of-mouth marke ng, diff usion of innova on, or buzz and viral marke ng 2 all aim to take advantage of the rela onships between users to facilitate the spread of awareness or adop on. In order to predetermine the eff ec veness of such campaigns, it is important to be able to es mate poten al return on investment. In par cular, the ability to model exis ng networks, track the propaga on of marke ng messages and es mate customer exposures and impressions are essen al for this purpose. A wide range of techniques to measure no ons such as user engagement on such pla orms have been developed and there also exists a signifi cant amount of research on modelling contagion and diff usion in network-based environments that can be exploited to generally refi ne an overall marke ng strategy. However, the structure and proper es of diff erent social media pla orms introduce various constraints on both the means via which data propagate and the visibility of content and nodes, constraints that must be taken into account when modelling or measuring the impact of social media campaigns. Perfect informa on about exposures within a given graph to a given message will not be available and as such it is important to inves gate and defi ne methodologies for diff usion monitoring that are suited to specifi c pla orms.

No abstract