PROJECT TITLE :

A Predictive Model for User Motivation and Utility Implications of Privacy-Protection Mechanisms in Location Check-Ins - 2018

ABSTRACT:

Location check-ins contain both geographical and semantic info regarding the visited venues. Semantic information is sometimes represented by means of tags (e.g., “restaurant”). Such knowledge will reveal some personal info regarding users beyond what they actually expect to disclose, hence their privacy is threatened. To mitigate such threats, many privacy protection techniques primarily based on location generalization have been proposed. Although the privacy implications of such techniques are extensively studied, the utility implications are largely unknown. During this Project, we propose a predictive model for quantifying the effect of a privacy-preserving technique (i.e., generalization) on the perceived utility of check-ins. We first study the users' motivations behind their location check-ins, primarily based on a study targeted at Foursquare users (N 1/4 77). We have a tendency to propose a machine-learning methodology for determining the motivation behind every check-in, and we have a tendency to design a motivation-primarily based predictive model for the utility implications of generalization. Primarily based on the survey data, our results show that the model accurately predicts the fine-grained motivation behind a check-in in [forty three%] of the cases and in [sixty threepercent] of the cases for the coarse-grained motivation. It conjointly predicts, with a mean error of [0.fifty two] (on a scale from 1 to five), the loss of utility caused by semantic and geographical generalization. This model makes it potential to style of utility-aware, privacy-enhancing mechanisms in location-based mostly on-line social networks. It conjointly enables service suppliers to implement locationsharing mechanisms that preserve each the utility and privacy for their users.