Application of semantic annotations to predicting users' demographics

  • Authors:
  • Blaž Fortuna;Dunja Mladenić;Marko Grobelnik

  • Affiliations:
  • Jožef Stefan Institute, Ljubljana, Slovenia;Jožef Stefan Institute, Ljubljana, Slovenia;Jožef Stefan Institute, Ljubljana, Slovenia

  • Venue:
  • ESAIR '10 Proceedings of the third workshop on Exploiting semantic annotations in information retrieval
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents an experimental study on predicting demographics for the users of a large news publishing web site. Each user is described by the articles he/she has read. The study looks at the effect of features used for article representations, such as text, automatic annotations and manually annotations on the prediction performance. It is show how different demographic dimensions depend on different combination of automatic and / or manual annotations.