ElGindy, Ehab and Abdelmoty, Alia ![]() ![]() |
Preview |
PDF
- Accepted Post-Print Version
Download (4MB) | Preview |
Abstract
Geo-folksonomies link social web users to geographic places through the tags users choose to label the places with. These tags can be a valuable source of information about the user’s perception of place and can reflect their experiences and activities in the places they label. By analysing the associations between users, places and tags, an understanding of a place and its relationships with other places can be drawn. This place characterisation is unique, dynamic and reflects the perception of a particular user community that generated the geo-folksonomy. In this work, an approach is proposed to analysing geo-folksonomies that builds on and extends existing statistical methods by considering specific concepts of relevance to geographic place resources, namely, place types and place-related activities, and by building a place ontology to encode those concepts and relationships. The folksonomy analysis and evaluation are demonstrated using a realistic geo-folksonomy data set. The resulting ontology is used to build user profiles from the folksonomy. The derived profiles reflect the association between users and the specific places they tag as well as other places with relevant associated place type and activities. The methods proposed here provide the potential for many interesting and useful applications, including the harvesting of useful insight on geographic space and employing the derived user profiles to enhance the search experience and to identify similarities between users based on their association to geographic places.
Item Type: | Article |
---|---|
Date Type: | Publication |
Status: | Published |
Schools: | Computer Science & Informatics |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Uncontrolled Keywords: | place ontology; geo-social web; user profile |
Publisher: | Taylor & Francis |
ISSN: | 1365-8816 |
Date of First Compliant Deposit: | 20 February 2017 |
Date of Acceptance: | 26 January 2014 |
Last Modified: | 22 Nov 2024 18:15 |
URI: | https://orca.cardiff.ac.uk/id/eprint/67917 |
Citation Data
Cited 7 times in Scopus. View in Scopus. Powered By Scopus® Data
Actions (repository staff only)
![]() |
Edit Item |