Towards a social media-based model of trust and its application

In this paper we describe the development of a model for measuring consumer trust in certain topics on the basis of social media. Specifically, we propose a model for trust that takes into account both textually expressed sentiment and source authority, and illustrate it on a specific case: the iCloud cloud computing service of Apple and its reception on Twitter. We demonstrate that it is possible to parameterize a trust function with weights that interpolate between the contribution of sentiment and the authority of the tweet senders. Feedback data containing perceived trust in the iCloud service was gathered from a community of users. On this data, our model was fitted and evaluated. Finally, we show how such a fitted model can be used as a basis for a visualization tool aimed at supporting professionals monitoring trust, or to simulate implications of interventions. Our approach is a first step towards a dynamic trust monitor that is a viable alternative to more rigid, survey-based approaches to measuring trust.