Cross Media Recommendation in Digital Library
Rapidly increasing volumes of heterogeneous media digital contents are produced into the digital library by the forms of the digital books, videos, images, etc. However, traditional recommendation approaches in the digital library cannot support the potential semantic connections across different types of media data. In this paper, a cross-media recommendation algorithm for the digital library is proposed, in which the retrieved items may come from different data sources, and the results do not need to be of the same media type the user ever read or tagged. Firstly, a fused user-item-feature tensor is used to represent the cross-media data set. Then the item-context latent space and item-user rating latent space are reconstructed by TUCKER based tensor decomposition. And the structural grouping sparsity approach is used to select the feature groups and the subset of homogeneous features in one group, which can deal with the difficulty of sparse and high dimension of the big feature matrix. Finally, the Top-n items are recommended according to the prediction probability estimated. Experiments conducted on a cross-media dataset based on China Academic Digital Associative Library (CADAL). The performances evaluation is based on the recall precision and diversity score. The experiment results show that our approach has good recommendation accuracy as well as good diversity.
KeywordsCross-media Recommendation Feature Selection Sparse Representation CADAL
Unable to display preview. Download preview PDF.
- 3.Ricci, F., Rokach, L., Shapira, B., Kantor, P.: Recommender Systems Handbook. Springer (2010)Google Scholar
- 5.Koren, Y., Bell, R.: Advances in collaborative filtering. In: Recommender Systems Handbook. Springer (2010)Google Scholar
- 7.Funk, S.: Netflix update: Try this at home (2006), http://sifter.org/?simon/journal/20061211.html
- 11.Harshman, R.A.: Foundations of the PARAFAC procedure: models and conditions for an “explanatory” multimodal factor analysis. University of California at Los Angeles (1970)Google Scholar
- 14.Wu, F., Han, Y., Tian, Q., Zhuang, Y.: Multi-label boosting for image annotation by structural grouping sparsity. In: Proceedings of the 2010 ACM International Conference on Multimedia (ACMMM), New York, NY, USA, pp. 15–24 (2010)Google Scholar
- 15.Ricci, F., Rokach, L., Shapira, B., Kantor, P.B. (eds.): Recommender Systems Handbook, 1st edn. Springer (2011)Google Scholar
- 16.Hill, W., Stead, L., Rosenstein, M., Furnas, G.: Recommending and evaluating choices in a virtual community of use. In: Proc. of the SIGCHI Conference on Human Factors in Computing Systems (CHI 1995), pp. 194–201 (1995)Google Scholar
- 18.Resnick, P., Iacovou, N., Suchak, M., Bergstorm, P., Riedl, J.: An open architecture for collaborative filtering of netnews. In: Proc. of the ACM Conference on Computer Supported Cooperative Work (CSCW 1994), pp. 175–186 (1994)Google Scholar
- 21.Schein, A.I., Popescul, A., Ungar, L.H., Pennock, D.M.: Methods and metrics for cold-start recommendations. In: Proc. of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2002), pp. 253-260 (2002)Google Scholar
- 22.Lops, P., de Gemmis, M., Semeraro, G.: Content based recommender systems: state of the art and trends. In: Recommender Systems Handbook. Springer (2010)Google Scholar
- 24.Schclar, A., Tsikinovsky, A., Rokach, L., Meisels, A., Antwarg, L.: Ensemble methods for improving the performance of neighborhood-based collaborative filtering. In: Proc. of the 3th ACM Conference on Recommender Systems, pp. 261–264 (2009)Google Scholar