Telling your story: autobiographical metadata and the semantic web


Tuffield, Mischa Moussavian (2010) Telling your story: autobiographical metadata and the semantic web. University of Southampton , School of Electronics and Computer Science , Doctoral Thesis , 180pp.

Download

[img] PDF
Download (10Mb)

Description/Abstract

Given the current explosion of user-generated content driven by the ever-decreasing price of sensing and storage hardware the dream of capturing and archiving the entirety of a human life is slowly being realised. The Semantic Web, a discipline of Computer Science, aims to support the sharing and interoperation of knowledge using the Web’s infrastructure. This thesis aims to roadmap a framework utilising the principles and technologies underpinning the Semantic Web, enabling the vision of global knowledge sharing, in an open and policy aware manner, with the end aim of supporting a network for the exploitation of personal information. This sharing is facilitated through the adoption of a lingua franca, shared conceptualisations for domain knowledge, and some core design principles. The main focus of Semantic Web research has been the development of a web-scale knowledge-base whereby information is stored and exposed in a machine-readable format with the ultimate aim of aggregating information from disparate sources, allowing for statements to be contextualised with respect to others culminating in a web-scale knowledge resource accessible through standard protocols.

The current popularity of social computing – Web 2.0 – where users post personal information to online communities is eluding to the fact that information, linked and shared within a social-context presents added value to the end-user. Given the sensitive nature of personal information, one may not wish to expose all of the information about them self to the World Wide Web, but may wish to benefit by linking to knowledge residing on this shared resource. This ability to store personal information privately, in ones own personal web-space and not on a third party server, whilst at the same time connecting to the publicly available information is presented as key challenge facing the Computer Science community today. Specific information pertaining to one aspect of a user’s activities, such as their picture taking habits or their geographic log, may not present a detailed account of a user’s actions, but as more information is pushed into the public domain and aggregation technologies mature individuals and their day-to-day activities will be easier to track.

As more and more of our personal lives are pushed into the public domain, the notion of an online-persona is becoming more and more applicable to the average person.

This thesis presents an infrastructure for the capturing and archival of autobiographical metadata, whereby information from multiple sensors is aggregated and stored in a personal Lifelog. The surrender of digital identity has become commonplace, for purposes ranging from commerce, marketing, social networking, government, receipt of services, travel or security, Lifelogging has the potential to reaffirm the individual’s control of his or her own digital identity. The Lifelog is a constructed identity that outweighs the others simply by weight of evidence, complexity and comprehensiveness.

This thesis presents an infrastructure for the capture and exploitation of personal metadata to drive research into context aware systems. The aim is to expose ongoing research in the areas of capture of personal experiences, context aware systems, multimedia annotation systems, narrative generation, all set in the context of enabling and supporting the Semantic Web Vision. The thesis details the work underway towards the goal of creating a multi-domain contextual log, and is followed by a discussion of how such a log can be used to drive the development of detailed Lifelog and an investigation into the amount of personal information being pushed into the public domain.

Item Type: Thesis (Doctoral)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: University Structure - Pre August 2011 > School of Electronics and Computer Science > Intelligence, Agents, Multimedia
ePrint ID: 159927
Date Deposited: 15 Jul 2010 15:42
Last Modified: 27 Mar 2014 19:16
URI: http://eprints.soton.ac.uk/id/eprint/159927

Actions (login required)

View Item View Item