Interpersonal trust measurements from social interactions in Facebook
Interpersonal trust is widely cited as an important component in several network systems such as peer-to-peer (P2P) networks, e-commerce and semantic web. However, there has been less research on measuring interpersonal trust due to the difficulty of collecting data that accurately reflects interpersonal trust. To address this issue, we quantify interpersonal trust by analyzing the social interactions between users and their friends on Facebook. Currently, friends of a user in almost all online social networks (OSN) are indistinguishable, i.e. there is no explicit indication of the strength of trust between a user and her close friends, as opposed to acquaintances. Existing research on estimating interpersonal trust in OSN faces two fundamental problems: the lacks of established dataset and a convincing evaluation method. In this thesis, we consider bidirectional interacting data in OSN to deconstruct a user's social behavior, and apply Principle Component Analysis (PCA) to estimate the interpersonal trust. A Facebook app, itrust, is developed to collect interaction data and calculate interpersonal trust. Moreover, we adopt the Kendall's tau and Generalized Kendall's tau methods to evaluate the accuracy of ranking list generated by itrust. Results show that itrust achieves more accurate interpersonal trust measurements than existing methods.