PhD Thesis Proposal Defence


"On The Use of Web Quality Dimensions For Finding High Quality Web Pages"

By Mr. Chun Chung Pun


Abstract:

Users can find information from the immense store of knowledge in the Web
with the help of a search engine. Nevertheless, users often complain about
the quality of the results returned. The quality is not necessarily only
limited to relevance, but also to other perspectives.

This research first examines what factors constitute a high quality
result; hence a framework of web quality dimension is proposed. From this
framework, it is found that current search engines only consider a very
small number of web data quality dimensions and they are typically
data-oriented (i.e., based on the subject or main theme of the web pages).
The user perspective (i.e., the user's preferences on specific web quality
dimensions) is rarely considered.

We then propose a general methodology for evaluating web quality metrics
derived from the web quality dimensions. The methodology has been applied
to two web quality dimensions, appropriateness and cohesiveness. Metrics
were developed to measure each dimension from a web page. They have been
verified to measure what users would expect.  In addition, it has been
shown that the metrics performed better at finding pages with the desired
quality than other systems.

The web quality dimension, appropriateness, measures how much the results
returned from search engines satisfy the web genre needs of a user. It is
based on the linguistic and visual complexity of a web page. The web
quality dimension, cohesiveness, is a measure of how closely the concepts
in a web page are related to each other. A distance metric is defined to
measure how close two concepts are in an ontology and the cohesiveness of
a web page is calculated as the total distances of all the concepts in it.
With these quality metrics, users can more easily find high quality (not
just relevant, but also to their desired dimensions) web pages.

In future we propose to do a larger scale user study to verify the
conformance of the metrics to the corresponding quality dimensions. In
addition, we would also propose a technique to integrate the quality
dimensions and to allow users to specify their preferences for them.


Date:     		Wednesday, 29 June 2005

Time:                   10:30a.m.-12:30p.m.

Venue:                  Room 2406
			lifts 17-18

Committee Members:      Prof. Frederick Lochovsky (Supervisor)
                        Dr. Wilfred Ng (Chairperson)
			Dr. Qiong Luo
			Prof. Vincent Shen


**** ALL are Welcome ****