Indirect Keyword Recommendation

Helping users to find useful contacts or potentially interesting subjects is a challenge for social and productive networks. The evidence of the content produced by users must be considered in this task, which may be simplified by the use of the meta-data associated with the content, i.e., The categ...

Full description

Saved in:
Bibliographic Details
Published in:2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) Vol. 1; pp. 384 - 391
Main Authors: Sabino, Andre, Rodrigues, Armanda, Goulao, Miguel, Gouveia, Joao
Format: Conference Proceeding
Language:English
Published: IEEE 01.08.2014
Subjects:
Analytical models
Collaborative work
Context
Feature extraction
Production
social graph
social network
Social network services
tagging
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Helping users to find useful contacts or potentially interesting subjects is a challenge for social and productive networks. The evidence of the content produced by users must be considered in this task, which may be simplified by the use of the meta-data associated with the content, i.e., The categorization supported by the network -- descriptive keywords, or tags. In this paper we present a model that enables keyword discovery methods through the interpretation of the network as a graph, solely relying on keywords that categorize or describe productive items. The model and keyword discovery methods presented in this paper avoid content analysis, and move towards a generic approach to the identification of relevant interests and, eventually, contacts. The evaluation of the model and methods is executed by two experiments that perform frequency and classification analyses over the Flickr network. The results show that we can efficiently recommend keywords to users.
DOI:10.1109/WI-IAT.2014.60