Recommendation systems and content filtering approaches based on annotationsand ratings, essentially rely on users expressing their preferences andinterests through their actions, in order to provide personalised content. Thisactivity, in which users engage collectively, has been named social tagging.Although it has opened a myriad of new possibilities for applicationinteroperability on the semantic web, it is also posing new privacy threats.Social tagging consists in describing online or online resources by usingfree-text labels (i.e. tags), therefore exposing the user's profile andactivity to privacy attacks. Tag forgery is a privacy enhancing technologyconsisting of generating tags for categories or resources that do not reflectthe user's actual preferences. By modifying their profile, tag forgery may havea negative impact on the quality of the recommendation system, thus protectinguser privacy to a certain extent but at the expenses of utility loss. Theimpact of tag forgery on content-based recommendation is, therefore,investigated in a real-world application scenario where different forgerystrategies are evaluated, and the consequent loss in utility is measured andcompared.
展开▼
