Project Triton : A study into delivering targeted information to an individual based on implicit and explicit data.

Abstract

The World Wide Web is frequently seen as a source of knowledge, however much of this remains undiscovered by its users. In recent times, recommender systems (e.g. Digg and Last.fm) have attempted to bridge this gap, alerting users to previously untapped knowledge. As more socially oriented services appear on the Web (e.g. Facebook and MySpace), it has never been easier to obtain information pertaining to an individual’s interests. At present, solutions for automated data recommendation tend to be highly topic specific (recommending only a certain topic such as news) and often only allow access to the system using monolithic interfaces. This report hopes to detail the stages from research to evaluation involved in creating an extensible framework, which will operate without the need for human intervention. The framework will feature several proof-of-concept plugins residing in a custom workflow, which target information that is useful to the user. Information will be retrieved automatically through plugins involved with data gathering (such as feed processing and page scraping), while users’ interests will be obtained implicitly (for example, using header information to derive location) or explicitly (taking advantage of Social Network APIs such as Facebook Connect). Finally, Third Parties will be able to integrate the framework into their own solutions using the customisable XML API (written in PHP), so that their products can provide custom user interfaces without style constraints.

More information

Identifiers

Catalogue record

Export record