Managing your own data

Our personal data is everywhere and should be controlled and managed by us, not others,  a University of Sydney expert will argue at this week’s  ACM Multimedia Conference in Brisbane.

Judy Kay, Professor of Computer Science says: “Our personal data resides in quite a bewildering range of places, from personal devices such as mobile phones to cloud stores, and also in a multitude of online silos.”

“Our personal data is captured by a rich digital ecosystem of devices, some worn, some carried, and others are fixed or embedded in the environment.

“While a person  does explicitly store some data, other systems are also capturing that person’s  digital footprints, ranging from simple clicks and touches, to images, audio and video,”  says Professor Kay.

In her ACM Multimedia presentation Professor Kay will present case studies of innovative uses of rich multi-media data as well as frameworks designed to empower people to harness and manage their personal data:

“Big personal data differs from the scientific big data in important ways. Because it is personal, we need to find better ways for technology to enable people to ensure it is managed and used as they wish.

“It may be of modest size compared with scientific big data, but in practical terms, people find that their data stores feel big, because they are complex and hard to manage.”

The Professor of Computer Science at the university's School of Information Technologies has long been working on many facets of the technology that can tackle the challenges of managing big personal data. These include creating a technical infrastructure, with representations and interfaces that allow a user to examine and control their own personal data in an easy to understand “user model”.

“One important role for users’ models is personalisation where the user model is a dynamic set of evidence-based beliefs about the user,” Professor Kay will tell her audience.

Existing user models can represent anything from the user’s attributes to their knowledge, beliefs, goals, plans and preferences.

Professor Kay says: “User modelling evidence can come directly from the user; for example, people typically provide online dating sites with rich (if not entirely accurate) descriptions of themselves and about the people they believe they would like.

“Plus much commercial user modelling evidence comes from observing the user. For example, a personalized teaching system observes the learner’s interactions, as they use learning resources and tackle problems. From this data the system infers what the learner knows. Web applications track people’s actions to drive personalised services and advertising,” Professor Kay says.