Use this URL to cite or link to this record in EThOS:
Title: Profile-based summarisation for web site navigation
Author: Alhindi, Azhar Hasan
ISNI:       0000 0004 6056 8183
Awarding Body: University of Essex
Current Institution: University of Essex
Date of Award: 2015
Availability of Full Text:
Access from EThOS:
Compared to information systems that work the same for all users and contexts, systems that utilise contextual information have greater potential to help a user identify relevant information more quickly and more accurately. Contextual information comes in a variety of flavours, often derived from records of past interactions between a user and the information system. It can be individual- or group-based. The motivation for our work is as follows. First, instead of looking at Web searching or browsing, which has been studied extensively, we focus our attention on Web sites. Such collections can be notoriously difficult to search or explore. If we could learn from past user interactions what information needs can be satisfied by which -documents, we would be in a position to help a new user to get to the required information much more rapidly. Hence, we harness the search behaviour of cohorts of users instead of individual users, turning it automatically into a profile which can then be used to assist other users of the same cohort. Finally, we are interested in exploring how such a profile is best utilised for profile-based summarisation of the collection at hand in a navigation scenario in which such summaries can be displayed as hover text as a user moves the mouse over a link. The process of acquiring the profile is not a research interest here; we simply adopt a biologically inspired method that resembles the idea of ant colony optimisation (AGO). This has been shown to work well in a variety of application areas. The model can be built in a continuous learning cycle that exploits search patterns as recorded in typical query log files. The main focus of this thesis will be on using the model in profile-based summarisation to generate summaries of documents for navigation support. Our research explores different single-document and multi- document summarisation techniques, some of which use the profile and some of which do not. We perform task-based evaluations of these different techniques - and hence of the impact of the profile and profile-based summarisation - in the context of Web site navigation. The experimental results demonstrate that profile-based summarisation to assist users in navigation tasks can significantly outperform generic summarisation as well as a standard Web site without such assistance.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available