Post-based collaborative filtering for personalized tag recommendation

  • Authors:
  • Caimei Lu;Xiaohua Hu;Jung-ran Park;Jia Huang

  • Affiliations:
  • Drexel University, Philadelphia, PA;Drexel University, Philadelphia, PA;Drexel University, Philadelphia, PA;Drexel University, Philadelphia, PA

  • Venue:
  • Proceedings of the 2011 iConference
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Social tagging provides a collaborative approach for information organization. The tags created by users in social tagging system not only contain rich semantic information about the described web objects, but also provide a window for information providers to learn a user's information interests and preferences. However, the tags created by a user for a document are always limited in terms of quantity and quality. Tag recommendation, especially personalized tag recommendation has been proposed as an approach to address this problem. In this paper, we develop a post-based collaborative filtering framework for personalized tag recommendation based on the tripartite social tagging network. The proposed method is evaluated and compared with a range of methods based on a real world social tagging dataset. The F-score and NDCG calculated to evaluate the recommendation results. The experimental results show that the proposed method can always generate the best results compared to other methods.