Private, sensitive information is exchanged at multiple levels of EEXCESS like for example during recommendation and usage mining. Our research depends to a large degree on objects (web-pages, documents etc.) providing information about their properties (i.e. they must contain metadata) and persons providing information about their usage behaviour (i.e. click-rates, technical details of the devices used etc.). In the case of people, this raises serious privacy protection issues.
Hence, privacy protection plays a large role in the research goals of EEXCESS. The project partners will research and develop methodologies and technologies for guaranteeing privacy-preserving augmentation, recommendation, and user mining.
At all stages of development, EEXCESS aims to retain full user privacy and user control. All user profiles and context information will be stored on the user’s device (instead of a central server), submitting only minimal necessary information to the recommender system. Data will only be collected with prior and express permission of users and anonymised.
Furthermore, we will design and implement a privacy proxy on the user’s device which is under full control of the user. The proxy will ensure that users can
(i) observe all traces via a graphical interface,
(ii) analyse a posteriori the activity of the proxy and the type and volume of exchanged data, and
(iii) allow the system (recommenders and digital libraries) to learn from the usage traces and improve their quality of service.
|The key objectives of EEXCESS:|
|1. Enrichment of content|
|2. Personalised recommendation|
|3. Privacy Preservation|