Abstract
Every day, millions of texts, images, audios, videos, and other information with different modalities are posted on social media. These multimodal data provide abundant resources for information recommendation. In this paper, a new method based on multimodal data fusion is proposed for more effective recommendation on social media. Firstly, a heterogeneous graph on texts and images is created effectively to represent the relationship of multimodal data. Then the relationship of multimodal data is fused based on graph clustering to improve the quality of social media recommendation. Finally, the multimodal social media information recommendation is performed as a process of walk on the proposed heterogeneous graph. The experiment on texts and images of microblogs shows social media recommendation using multimodal data fusion is better than that on single modality.
Keywords
Project supported by the State Key Development Program for Basic Research of China (Grant No. 2011CB302200-G), the National Natural Science Foundation of China under Grant No. 61370074, 61100026.
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
Massoudi, K., Tsagkias, M., de Rijke, M., Weerkamp, W.: Incorporating query expansion and quality indicators in searching microblog posts. In: Clough, P., Foley, C., Gurrin, C., Jones, G.J.F., Kraaij, W., Lee, H., Mudoch, V. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 362–367. Springer, Heidelberg (2011)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Ling, H., Yan, L., Zou, F., et al.: Fast image copy detection approach based on local fingerprint defined visual words. Signal Process 93, 2328–2338 (2013)
Datar, M., Indyk, P., Immorlica, N., et al.: Locality-sensitive hashing scheme based on p-stable distributions. In: 20th SCG, pp. 253–262. ACM, NY (2004)
Xu, X., Yuruk, N., Feng, Z., et al.: SCAN: A structural clustering algorithm for networks. In: 13th SIGKDD, pp. 824–833. ACM, NY (2007)
Zhao, W.-L., Jegou, H., Gravier, G.: Sim-Min-Hash: An efficient matching technique for linking large image collections. In: 21st MM, pp. 577–580. ACM, NY (2013)
Krapac, J., Allan, M., Verbeek, J., et al.: Improving web image search results using query-relative classifiers. In: CVPR, pp. 1094–1101. IEEE (2010)
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
Xiong, Y., Wang, D., Zhang, Y., Feng, S., Wang, G. (2014). Multimodal Data Fusion in Text-Image Heterogeneous Graph for Social Media Recommendation. In: Li, F., Li, G., Hwang, Sw., Yao, B., Zhang, Z. (eds) Web-Age Information Management. WAIM 2014. Lecture Notes in Computer Science, vol 8485. Springer, Cham. https://doi.org/10.1007/978-3-319-08010-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-08010-9_12
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08009-3
Online ISBN: 978-3-319-08010-9
eBook Packages: Computer ScienceComputer Science (R0)