Using profiling techniques to protect the user's privacy in twitter

  • Authors:
  • Alexandre Viejo;David Sánchez;Jordi Castellà-Roca

  • Affiliations:
  • Departament d'Enginyeria Informàtica i Matemàtiques, UNESCO Chair in Data Privacy, Universitat Rovira i Virgili, Tarragona, Spain;Departament d'Enginyeria Informàtica i Matemàtiques, UNESCO Chair in Data Privacy, Universitat Rovira i Virgili, Tarragona, Spain;Departament d'Enginyeria Informàtica i Matemàtiques, UNESCO Chair in Data Privacy, Universitat Rovira i Virgili, Tarragona, Spain

  • Venue:
  • MDAI'12 Proceedings of the 9th international conference on Modeling Decisions for Artificial Intelligence
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The emergence of microblogging-based social networks shows how important it is for common people to share information worldwide. In this environment, Twitter has set it apart from the rest of competitors. Users publish text messages containing opinions and information about a wide range of topics, including personal ones. Previous works have shown that these publications can be analyzed to extract useful information for the society but also to characterize the users who generate them and, hence, to build personal profiles. This latter situation poses a serious threat to users' privacy. In this paper, we present a new privacy-preserving scheme that distorts the real user profile in front of automatic profiling systems applied to Twitter. This is done while keeping user publications intact in order to interfere the least with her followers. The method has been tested using Twitter publications gathered from renowned users, showing that it effectively obfuscates users' profiles.