Abstract
We formally propose a new application problem: unsupervised text-image topic discovery. The application problem is important because almost all news articles have one picture associated. Unlike traditional topic modeling which considers text alone, the new task aims to discover heterogeneous topics from web news of multiple data types. The heterogeneous topic discovery is challenging because different media data types have different characteristics and structures, and a systematic solution that can integrate information propagation and mutual enhancement between data of different types in a principle way is not easy to obtain, especially when no supervision information is available. We propose to tackle the problem by a regularized nonnegative constrained l 2,1-norm minimization framework. We also present a new iterative algorithm to solve the optimization problem. To objectively evaluate the proposed method, we collect two real world text-image web news datasets. Experimental results show the effectiveness of the new approach.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Blei, D., Ng, A., Jordan, M.: Latent dirichlet allocation. The Journal of Machine Learning Research 3, 993–1022 (2003)
Cai, X., Nie, F., Huang, H.: Multi-view k-means clustering on big data. In: Proceedings of the 23rd International Joint Conference on Artificial Intelligence (2013)
Chen, Y., Wang, L., Dong, M.: Non-negative matrix factorization for semisupervised heterogeneous data coclustering. IEEE Transactions on Knowledge and Data Engineering (2010)
Deerwester, S., Dumais, S., Furnas, G., Landauer, T., Harshman, R.: Indexing by latent semantic analysis. Journal of the American Society for Information Science 41(6), 391–407 (1990)
Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 50–57. ACM (1999)
Kong, D., Ding, C., Huang, H.: Robust nonnegative matrix factorization using l21-norm. In: Proceedings of the 20th ACM International conference on Information and Knowledge Management, pp. 673–682. ACM (2011)
Kumar, A., Daumé III, H.: A co-training approach for multi-view spectral clustering. In: Proceedings of the 28th Annual International Conference on Machine Learning (2011)
Meng, L., Tan, A., Xu, D.: Semi-supervised heterogeneous fusion for multimedia data co-clustering. IEEE Transactions on Knowledge and Data Engineering (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Qian, M. (2014). Text-Image Topic Discovery for Web News Data. In: de Rijke, M., et al. Advances in Information Retrieval. ECIR 2014. Lecture Notes in Computer Science, vol 8416. Springer, Cham. https://doi.org/10.1007/978-3-319-06028-6_75
Download citation
DOI: https://doi.org/10.1007/978-3-319-06028-6_75
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06027-9
Online ISBN: 978-3-319-06028-6
eBook Packages: Computer ScienceComputer Science (R0)