Tagvisor: A Privacy Advisor for Sharing Hashtags

TL;DR

This paper analyzes privacy risks associated with hashtags, especially location inference, and introduces Tagvisor, a system that suggests alternative hashtags to protect user privacy while maintaining utility.

Contribution

It presents the first systematic analysis of hashtag-induced privacy issues and proposes Tagvisor, a novel system with obfuscation techniques to balance privacy and utility.

Findings

Location can be inferred from hashtags with 70-76% accuracy.

Obfuscating two hashtags achieves a near-optimal privacy-utility trade-off.

Tagvisor is highly time-efficient and practical for real-world use.

Abstract

Hashtag has emerged as a widely used concept of popular culture and campaigns, but its implications on people's privacy have not been investigated so far. In this paper, we present the first systematic analysis of privacy issues induced by hashtags. We concentrate in particular on location, which is recognized as one of the key privacy concerns in the Internet era. By relying on a random forest model, we show that we can infer a user's precise location from hashtags with accuracy of 70\% to 76\%, depending on the city. To remedy this situation, we introduce a system called Tagvisor that systematically suggests alternative hashtags if the user-selected ones constitute a threat to location privacy. Tagvisor realizes this by means of three conceptually different obfuscation techniques and a semantics-based metric for measuring the consequent utility loss. Our findings show that obfuscating as little as two hashtags already provides a near-optimal trade-off between privacy and utility in our dataset. This in particular renders Tagvisor highly time-efficient, and thus, practical in real-world settings.