Odysseus

Twitter is one of the surprise success stories of the last couple of years and today 10s of millions of users are happily sharing their thoughts, opinions, and insights with their friends and followers, all in the form of 140-charater short text messages.

In CLARITY we have a large screen that displays tweets which are deemed important to the people in the office. Although the content changes dynamically, the sources of these feeds is static and does not change based on the people in the office, even though there is often different groups moving through the office space. At the same time, everyone nowadays carries around a bluetooth enabled device be it a mobile phone or a laptop.

In this project, the student will develop an application which can recommend personalised twitter and news output based on the the range of people currently in range of the output. The student will develop a bluetooth spotter which will be able to detect and log when registered users are present in the office. Based on the people present, the application will tailor and personalise the content output to the large-screen. Machine learning and information retrieval techniques will be used to compile the appropriate output.

The student will benefit from access to a number of CLARITY researchers who are working on related issues. CLARITY has a large database of recorded tweets which can be used for development and testing. This project affords students the opportunity to work with interesting technologies and programming languages such as Bluetooth, Java and Adobe Flex.

Workplan

Weeks 1-2: Background Research. Gain understanding of bluetooth technologies and the twitter api. Come up with an overall design for the application.

Weeks 3-4: Develop the bluetooth spotter and user registration/logging parts of the application.

Weeks 5-7: Develop personalised output algorithm combining user profiles and twitter/news sources.

Weeks 8-10: Design and implement dynamic interface for displaying personalised output.

Supporting Material:
Adobe Flex http://www.adobe.com/devnet/flex/
Java & Bluetooth http://www.javabluetooth.com/
Twitter API http://apiwiki.twitter.com/