Augmenting Navigation for Collaborative Tagging with Emergent Semantics
M. Aurnhammer, P. Hanappe, and L. Steels. 5th International Semantic Web Conference, ISWC 2006, Athens, GA, USA, volume 4273 of Lecture Notes in Computer Science, page 58--71. Springer-Verlag, (5-9 nov 2006)
Abstract
We propose an approach that unifies browsing by tags and visual features for intuitive exploration of image databases. In contrast to traditional image retrieval approaches, we utilise tags provided by users on collaborative tagging sites, complemented by simple image analysis and classification. This allows us to find new relations between data elements. We introduce the concept of a navigation map, that describes links between users, tags, and data elements for the example of the collaborative tagging site Flickr. We show that introducing similarity search based on image features yields additional links on this map. These theoretical considerations are supported by examples provided by our system, using data and tags from real Flickr users.
%0 Conference Paper
%1 Aurnhammer:2006_808
%A Aurnhammer, Melanie
%A Hanappe, Peter
%A Steels, Luc
%B 5th International Semantic Web Conference, ISWC 2006, Athens, GA, USA
%D 2006
%E Cruz, Isabel F.
%E Decker, Stefan
%E Allemang, Dean
%E Preist, Chris
%E Schwabe, Daniel
%E Mika, Peter
%E Uschold, Michael
%E Aroyo, Lora
%I Springer-Verlag
%K flickr, folksonomy, navigation, website
%P 58--71
%T Augmenting Navigation for Collaborative Tagging with Emergent Semantics
%V 4273
%X We propose an approach that unifies browsing by tags and visual features for intuitive exploration of image databases. In contrast to traditional image retrieval approaches, we utilise tags provided by users on collaborative tagging sites, complemented by simple image analysis and classification. This allows us to find new relations between data elements. We introduce the concept of a navigation map, that describes links between users, tags, and data elements for the example of the collaborative tagging site Flickr. We show that introducing similarity search based on image features yields additional links on this map. These theoretical considerations are supported by examples provided by our system, using data and tags from real Flickr users.
@inproceedings{Aurnhammer:2006_808,
abstract = {We propose an approach that unifies browsing by tags and visual features for intuitive exploration of image databases. In contrast to traditional image retrieval approaches, we utilise tags provided by users on collaborative tagging sites, complemented by simple image analysis and classification. This allows us to find new relations between data elements. We introduce the concept of a navigation map, that describes links between users, tags, and data elements for the example of the collaborative tagging site Flickr. We show that introducing similarity search based on image features yields additional links on this map. These theoretical considerations are supported by examples provided by our system, using data and tags from real Flickr users.},
added-at = {2007-07-06T02:12:29.000+0200},
author = {Aurnhammer, Melanie and Hanappe, Peter and Steels, Luc},
biburl = {https://www.bibsonomy.org/bibtex/222974100f52e50de47ec56483804507a/jrsinclair},
booktitle = {5th International Semantic Web Conference, ISWC 2006, Athens, GA, USA},
day = {5-9},
editor = {Cruz, Isabel F. and Decker, Stefan and Allemang, Dean and Preist, Chris and Schwabe, Daniel and Mika, Peter and Uschold, Michael and Aroyo, Lora},
interhash = {a9d35e917da138f929b5d81f1dab4fd0},
intrahash = {22974100f52e50de47ec56483804507a},
keywords = {flickr, folksonomy, navigation, website},
month = nov,
pages = {58--71},
publisher = {Springer-Verlag},
series = {Lecture Notes in Computer Science},
timestamp = {2007-07-06T02:12:29.000+0200},
title = {Augmenting Navigation for Collaborative Tagging with Emergent Semantics},
volume = 4273,
year = 2006
}