Thesis Topic Details

Topic ID:
3376
Title:
Personalisation of web pages using Natural Language Processing
Supervisor:
Tim Moors
Research Area:
Natural Language Processing, Networks
Associated Staff
Assessor:
Mahbub Hassan
Topic Details
Status:
Active
Type:
R & D
Programs:
CS SE
Group Suitable:
Yes
Industrial:
Pre-requisites:
--
Description:
People vary in their backgrounds, so even if they want to read about the same content, they might want different presentations of that content. For example, an expert in a field might appreciate the conciseness of abbreviations or generalised abstractions, whereas a novice might want abbreviations expanded with links to full definitions and might prefer concrete examples, an American might want imperial units whereas most of the rest of the world want metric, etc. Traditionally this has been solved through multiple authors (re)creating content (e.g. books) targeted at particular audiences. However, with digitised information (e.g. web pages) there is both the capacity to automate some personalisation at the consumer end (e.g. ebook reader, phone or computer) and increasingly there is a need for such personalisation as people seek ever-more specialised information which may be available from few authors. The goal of this project is to apply NLP techniques (e.g. word stemming to identify key words which can then be presented according to the user's taste) to develop software that can automatically personalise web pages.
Comments:
The supervisor is a Senior Lecturer in the School of Electrical Engineering and Telecommunications http://www2.eet.unsw.edu.au/~timm
Past Student Reports
 
No Reports Available. Contact the supervisor for more information.

Check out all available reports in the CSE Thesis Report Library.

NOTE: only current CSE students can login to view and select reports to download.