Automatic tagging based on Linked Data

Automatic tagging based on Linked Data

We have created a web agent for collecting Call for Papers (CFP) announcements. Our web agent obtains CFP announcements from websites or from mailbox. The most important information is extracted and published on our own special website in a user and machine readable way. One of the most important problems is event classification, categorization and clustering. In this paper we describe unsupervised methods for automatic tagging based on information extraction from Linked data. These methods are usable in situations where we have to tag unknown data and we have no corpus for learning methods. Tagged data can have the form of short messages from RSS, short blog posts or emails. The automatic tags can be used for classifying the conferences. Users can use our web service to search for interesting events and sort them by their own preferences. We obtain tags with their relationship parameters and we can use them for automatic clustering of collected events.

Keywords: Automatic tagging; Semantic Web; Web 2.0; Linked Data

Year: 2010

Authors of this publication:

Martin Dostal


Martin graduated from the University of West Bohemia in 2009, specialized in software engineering. He is interested in the semantic Web, information retrieval, and question answering.

Karel Je┼żek

Phone:  +420 377632475

Karel is the former group coordinator and a supervisor of PhD students working at research projects of this Group.

Related Projects:


Document Clustering and Linked Data

Authors:  Karel Je┼żek, Martin Dostal
Desc.:Unsupervised methods for automatic tagging and clustering based on information extraction from Linked data.