Tag Ranking by Linear Relational Neighbourhood Propagation

Author

Chidlovskii, Boris

Author_Institution

Xerox Res. Centre Eur., Meylan, France

fYear

2012

fDate

26-29 Aug. 2012

Firstpage

184

Lastpage

188

Abstract

We propose a tag recommendation method which can assist users in tagging process by suggesting relevant tags. The method is based on query-based ranking on relational multi-type graphs which capture the annotation relationship between objects and tags, as well as the object similarity and tag correlation. The additional advance consists in extending the linear neighbourhood propagation to the relational graphs with the Laplacian regularization framework. We report evaluation results on a large-scale Flickr data set.

Keywords

graph theory; query processing; recommender systems; social networking (online); Laplacian regularization framework; large-scale Flickr data set; linear relational neighbourhood propagation; object similarity; object-tag annotation relationship; query-based ranking; relational graphs; relational multitype graphs; tag correlation; tag ranking; tag recommendation method; tagging process; Correlation; Image edge detection; Image reconstruction; Laplace equations; Minimization; Tagging; Vectors; Laplacian regularization; Tag ranking; linear neighbourhood propagation; relational graphs;

fLanguage

English

Publisher

ieee

Conference_Titel

Advances in Social Networks Analysis and Mining (ASONAM), 2012 IEEE/ACM International Conference on

Conference_Location

Istanbul

Print_ISBN

978-1-4673-2497-7

Type

conf

DOI

10.1109/ASONAM.2012.40

Filename

6425765