Abstract
With the rapid development of location-based social networks (LBSNs), multimedia topic modeling on location-related user generated contents (UGCs) for venues is strongly desired. However, most of the previous topic modeling approaches only work on single modality data, or correlated multimodal data. The intrinsic property of UGCs in LBSNs that the heterogeneous UGCs are generally independent makes these approaches unsuitable for multimedia venue topic modeling. In this paper, we propose a novel multimedia topic modeling approach for extracting venue semantics from heterogeneous location-related UGCs. The approach relates multimedia UGCs by leveraging on multiple data sources. Furthermore, a graph clustering method is proposed to detect the topics which are considered as the dense subgraphs. Based on the multimedia venue topic modeling, we further propose the semantic based venue summarization, which verifies the effectiveness of the proposed framework. The integration of these heterogeneous UGCs into semantic topics provides users with an easier way to understand the venues, and therefore enriches the user experience. Extensive experiments have been conducted on a cross-platform dataset and promising results have been obtained.
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
Ahonen, T., Hadid, A., Pietikainen, M.: Face description with local binary patterns: Application to face recognition. IEEE TPAMI 28(12), 2037–2041 (2006)
Anaya-Sánchez, H., Porrata, A.P., Llavori, R.B.: A document clustering algorithm for discovering and describing topics. Pattern Recognition Letters (2010)
Blei, D.M., Jordan, M.I.: Modeling annotated data. In: SIGIR (2003)
Chen, K., Luesukprasert, L., Chou, S.T.: Hot topic extraction based on timeline analysis and multidimensional sentence modeling. In: IEEE TKDE (2007)
Chen, T., Liu, C., Huang, Q.: An effective multi-clue fusion approach for web video topic detection. In: ACM MM (2012)
Fang, Q., Sang, J., Xu, C., Lu, K.: Paint the city colorfully: Location visualization from multiple themes. In: Li, S., El Saddik, A., Wang, M., Mei, T., Sebe, N., Yan, S., Hong, R., Gurrin, C. (eds.) MMM 2013, Part I. LNCS, vol. 7732, pp. 92–105. Springer, Heidelberg (2013)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE TPAMI 32(9) (2010)
Gao, Y., Tang, J., Hong, R., Dai, Q., Chua, T.-S., Jain, R.: W2go: A travel guidance system by automatic landmark ranking. In: MM, pp. 123–132 (2010)
Ji, R., Gao, Y., Zhong, B., Yao, H., Tian, Q.: Mining flickr landmarks by modeling reconstruction sparsity. TOMCCAP 7S(1), 31:1–31:22 (2011)
Kurashima, T., Iwata, T., Hoshide, T., Takaya, N., Fujimura, K.: Geo topic model: joint modeling of user’s activity area and interests for location recommendation. In: WSDM (2013)
Liu, H., Yan, S.: Robust clustering as ensembles of affinity relations. In: NIPS (2010)
Liu, H., Yan, S.: Robust graph mode seeking by graph shift. In: ICML (2010)
Pan, C., Mitra, P.: Event detection with spatial latent dirichlet allocation. In: JCDL (2011)
Putthividhya, D., Attias, H.T., Nagarajan, S.S.: Topic regression multi-modal latent dirichlet allocation for image annotation. In: CVPR (2010)
Sang, J., Xu, C.: Browse by chunks: Topic mining and organizing on web-scale social media. TOMCCAP 7S(1), 30:1–30:18 (2011)
Virtanen, S., Jia, Y., Klami, A., Darrell, T.: Factorized multi-modal topic model. CoRR, abs/1210.4920 (2012)
Wang, Q., Xu, J., Li, H., Craswell, N.: Regularized latent semantic indexing: A new approach to large-scale topic modeling. ACM TOIS (2013)
Wang, X., Grimson, E.: Spatial latent dirichlet allocation. In: NIPS (2007)
Wu, Z., Palmer, M.S.: Verb semantics and lexical selection. In: ACL (1994)
Zhang, Y., Li, G., Chu, L., Wang, S., Zhang, W., Huang, Q.: Cross-media topic detection: A multi-modality fusion framework. In: ICME (2013)
Zhao, Y.-L., Zheng, Y.-T., Zhou, X., Chua, T.-S.: Generating representative views of landmarks via scenic theme detection. In: Lee, K.-T., Tsai, W.-H., Liao, H.-Y.M., Chen, T., Hsieh, J.-W., Tseng, C.-C. (eds.) MMM 2011 Part I. LNCS, vol. 6523, pp. 392–402. Springer, Heidelberg (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Nie, W., Wang, X., Zhao, YL., Gao, Y., Su, Y., Chua, TS. (2013). Venue Semantics: Multimedia Topic Modeling of Social Media Contents. In: Huet, B., Ngo, CW., Tang, J., Zhou, ZH., Hauptmann, A.G., Yan, S. (eds) Advances in Multimedia Information Processing – PCM 2013. PCM 2013. Lecture Notes in Computer Science, vol 8294. Springer, Cham. https://doi.org/10.1007/978-3-319-03731-8_53
Download citation
DOI: https://doi.org/10.1007/978-3-319-03731-8_53
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03730-1
Online ISBN: 978-3-319-03731-8
eBook Packages: Computer ScienceComputer Science (R0)