Authors:
Miltiadis Kandias
;
Lilian Mitrou
;
Vasilis Stavrou
and
Dimitris Gritzalis
Affiliation:
Athens University of Economics & Business, Greece
Keyword(s):
Awareness, Panopticon, Privacy, Social Media, Surveillance, User Profiling, YouTube.
Related
Ontology
Subjects/Areas/Topics:
Data and Application Security and Privacy
;
Information and Systems Security
;
Personal Data Protection for Information Systems
;
Privacy
;
Security and Privacy in Social Networks
Abstract:
Social media and Web 2.0 have enabled internet users to contribute online content, which may be crawled
and utilized for a variety of reasons, from personalized advertising to behaviour prediction/profiling. One
negative case scenario is the political affiliation profiling. Our hypothesis is that this scenario is nowadays
realistic, applicable to social media, and violates civil rights, privacy and freedom. To demonstrate this, we
developed a horror story, i.e., a Panopticon method, in order to reveal this threat and contribute in raising
the social awareness over it. The Panopticon relies on data/opinion mining techniques; hence it classifies
comments, videos and playlists, collected from the popular social medium YouTube. Afterwards, it aggregates
these classifications in order to decide over the users’ political affiliation. The experimental test case
of the Panopticon is an extensive Greek community of YouTube users. In order to demonstrate our case, we
performed an exte
nsive graph theoretical and content analysis of the collected dataset and show how and
what kind of personal data (e.g. political attitude) can be derived via data mining on publicly available
YouTube data. Then, we provide the reader with an analysis of the legal means that are available today, to a
citizen or a society as a whole, so as to effectively be prevented from such a threat.
(More)