ABSTRACT
Accurate and effective discovery of a brand's key assets, namely, Key Opinion Leaders (KOLs) and potential customers, plays an essential role in marketing campaigns. In a massive online social network, brands are challenged with identifying a small portion of key assets over an enormous volume of irrelevant users, making the problem a highly imbalanced one. Moreover, having to deal with social media data that are usually high-dimensional, the task of brand key asset discovery can be immensely expensive yet inaccurate if the information are not processed efficiently to extract representative features from the original space prior to the learning process. To address the above issues, we propose a novel method dubbed Cluster-wise Biased Discriminant Projection (CBDP) to uncover the compact and informative features from users' data for brand key asset discovery. CBDP conducts a two-layer learning procedure. In the first layer, a Discriminant Clustering (DC) scheme is developed to partition the original dataset into clusters with maximum discriminant capacity. In the second layer, a Biased Discriminant Projection (BDP) algorithm is proposed and performed on each cluster to map the high-dimensional data to the low-dimensional subspace, where the discriminant information of classes with high importance/preference is preserved. A unified mapping function of CBDP is finally established by integrating these two layers. Experiments on both synthetic examples and a real-world brand key asset dataset validate the effectiveness of the proposed method.
- M. Belkin and P. Niyogi. 2001. Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering. In NIPS 14. 585--591. Google ScholarDigital Library
- P. D. Berger and N. I. Nasr. 1998. Customer lifetime value: Marketing models and applications. Journal of interactive marketing 12, 1 (1998), 17--30.Google ScholarCross Ref
- B. Bi, L. Ji, and Q. Hu. 2008. Comparative Study on Classification Techniques to Identify Potential Customers. In Proc. ISCID, Vol. 2. 308--311. Google ScholarDigital Library
- C.-C. Chang and C.-J. Lin. 2011. LIBSVM: A Library for Support Vector Machines. ACM Trans. Intell. Syst. Technol. 2, 3 (2011), 27:1--27:27. Google ScholarDigital Library
- J. P. Cunningham and Z. Ghahramani. 2015. Linear Dimensionality Reduction: Survey, Insights, and Generalizations. Journal of Machine Learning Research 16 (2015), 2859--2900. Google ScholarDigital Library
- Z. Fan, Y. Xu, and D. Zhang. 2011. Local Linear Discriminant Analysis Framework Using Sample Neighbors. IEEE Trans. Neural Netw. 22, 7 (2011), 1119--1132. Google ScholarDigital Library
- R. A. Fisher. 1936. The Use of Multiple Measurements in Taxonomic Problems. Ann. Eugen. 7 (1936), 179--188.Google ScholarCross Ref
- X. He, S. Yan, Y. Hu, P. Niyogi, and H.-J. Zhang. 2005. Face recognition using Laplacianfaces. IEEE Trans. Pattern Anal. Mach. Intell. 27, 3 (2005), 328--340. Google ScholarDigital Library
- H. Hotelling. 1933. Analysis of a Complex of Statistical Variables Into Principal Components. J. Edu. Psychol. 24 (1933), 417--441, 498--520.Google ScholarCross Ref
- F. Li and T. C. Du. 2011. Who is talking? An ontology-based opinion leader identification framework for word-of-mouth marketing in online social blogs. Decision Support Systems 51, 1 (2011), 190--197. Google ScholarDigital Library
- Y. Liu, Z. Gu, and Y.-M. Cheung. 2016. Supervised Manifold Learning for Media Interestingness Prediction. In Proc. of the MediaEval 2016 Workshop.Google Scholar
- Y. Liu, Y. Liu, K. C. C. Chan, and K. A. Hua. 2014. Hybrid Manifold Embedding. IEEE Trans. Neural Netw. Learn. Syst. 25, 12 (2014), 2295--2302.Google ScholarCross Ref
- D. Luo, F. Nie, C. Ding, and H. Huang. 2011. Multi-subspace representation and discovery. In ECML/PKDD. 405--420. Google ScholarDigital Library
- F. Nie, W. Zhu, and X. Li. 2017. Unsupervised Large Graph Embedding. In Proc. 31st AAAI. 2422--2428.Google Scholar
- T. Ojala, M. Pietikainen, and T. Maenpaa. 2002. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24, 7 (2002), 971--987. Google ScholarDigital Library
- A. Rajaraman and J. D. Ullman. 2011. Mining of Massive Datasets. Cambridge University Press, New York, NY, USA. Google ScholarDigital Library
- A. Rodriguez and A. Laio. 2014. Clustering by fast search and find of density peaks. Science 344, 6191 (2014), 1492--1496.Google Scholar
- Bernhard Schölkopf, Alex J. Smola, Robert C. Williamson, and Peter L. Bartlett. 2000. New Support Vector Algorithms. Neural Comput. 12, 5 (2000), 1207--1245. Google ScholarDigital Library
- H. Sharara, L. Getoor, and M. Norton. 2011. Active Surveying: A Probabilistic Approach for Identifying Key Opinion Leaders. In Proc. 22nd IJCAI. 1485--1490. Google ScholarDigital Library
- S. Yan, Y. Hu, D. Xu, H.-J. Zhang, B. Zhang, and Q. Cheng. 2007. Nonlinear Discriminant Analysis on Embedded Manifold. IEEE Trans. Cir. and Sys. for Video Technol. 17, 4 (2007), 468--477. Google ScholarDigital Library
- Z. Zhai, H. Xu, and P. Jia. 2008. Identifying Opinion Leaders in BBS. In Proc. IEEE/WIC/ACM WI-IAT'08, Vol. 3. 398--401. Google ScholarDigital Library
Index Terms
- Brand key asset discovery via cluster-wise biased discriminant projection
Recommendations
Lorentzian discriminant projection and its applications
ACCV'09: Proceedings of the 9th Asian conference on Computer Vision - Volume Part IIIThis paper develops a supervised dimensionality reduction method, Lorentzian Discriminant Projection (LDP), for discriminant analysis and classification Our method represents the structures of sample data by a manifold, which is furnished with a ...
Kernel class-wise locality preserving projection
In the recent years, the pattern recognition community paid more attention to a new kind of feature extraction method, the manifold learning methods, which attempt to project the original data into a lower dimensional feature space by preserving the ...
Neighborhood discriminant projection for face recognition
We propose a novel manifold learning approach, called Neighborhood Discriminant Projection (NDP), for robust face recognition. The purpose of NDP is to preserve the within-class neighboring geometry of the image space, while keeping away the projected ...
Comments