Improving web information retrieval using shared contexts

Simple item page
aut.researcherMacDonell, Stephen Gerard
dc.contributor.authorConnor, AM
dc.contributor.authorLimbu, DK
dc.contributor.authorMacDonell, SG
dc.contributor.authorPears, R
dc.date.accessioned2011-10-12T04:10:19Z
dc.date.available2011-10-12T04:10:19Z
dc.date.copyright2010
dc.date.issued2010
dc.description.abstractThe effective utilisation of a user’s context in improving the performance of web search engines is a subject of intense research interest. In particular, much attention has been directed to the enhancement of queries and the provision of more relevant information by taking user context into account. Progress in this field has been limited to date, however, due to ongoing challenges in capturing and representing contextual information. We describe here the development and evaluation of a web-based contextual information retrieval that addresses some of these challenges and makes progress in defining the information required to create contextual profiles. Our system collects and leverages implicit and explicit user data to modify queries with the aim of more accurately reflecting the user’s interests. This data is maintained dynamically in each user’s contextual profile and utilised to improve the quality of information found during web searches. Where enabled, this data also contributes to the development of a shared contextual knowledge base that can also be used to augment queries. This shared contextual knowledge base is a key aspect of this research. The system has been tested in an observational study that has considered its ability to improve the user’s web search experience. This paper presents experimental data to provide evidence of the system’s performance, demonstrating that the shared contextual knowledge base extends the functionality associated with the individual contextual profile.
dc.identifier.citationInternational Journal of Information Sciences and Computer Engineering, vol.1(2), pp.26 - 35
dc.identifier.issn1836-7305
dc.identifier.roid18738en_NZ
dc.identifier.urihttps://hdl.handle.net/10292/2248
dc.publisherInformation Sciences and Computer Engineering
dc.relation.urihttp://www.ijisce.org/published.php?p=4&volume=1&issueno=2
dc.rightsInternational Journal of Information Sciences and Computer Engineering (IJISCE) (http://www.ijisce.org) is a free online access and peer-reviewed journal which publishes quarterly.
dc.rights.accessrightsOpenAccess
dc.subjectPersonalized web search
dc.subjectContextual search
dc.subjectRelevance feedback
dc.subjectQuery formulation
dc.titleImproving web information retrieval using shared contexts
dc.typeJournal Article
pubs.organisational-data/AUT
pubs.organisational-data/AUT/Design & Creative Technologies
pubs.organisational-data/AUT/PBRF Researchers
pubs.organisational-data/AUT/PBRF Researchers/Design & Creative Technologies PBRF Researchers
pubs.organisational-data/AUT/PBRF Researchers/Design & Creative Technologies PBRF Researchers/DCT C & M Computing
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Connor, Limbu, MacDonell and Pears (2010) IJISCE.pdf
Size:
465.27 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
licence.htm
Size:
29.98 KB
Format:
Unknown data format
Description:
Download
Collections
SERL - Software Engineering Research Laboratory