ABSTRACT
Influence maximization (IM) targets at maximizing the number of users being aware of a product by finding a set of seed users to expose in a social network. Previous IM models mainly focus on optimizing the spread of product consumption, which assumes that all users are potential customers and more exposures lead to better profit. However, in the real-world scenario, some people may not like the product and may express negative opinions after consuming, which damage the product reputation and harm the long-term profit. Only a portion of users in the social network, called the target user, is the potential customer that likes the product and will spread positive opinion. In this paper, we consider a problem called AcTive Opinion Maximization (ATOM), where the goal is to find a set of seed users to maximize the overall opinion spread toward a target product in a multi-round campaign. Different from previous works, we do not assume the user opinion is known before consumption, but should be derived from user preference data. The ATOM problem has essential applications in viral marketing, such as reputation building and precision advertising. Given its significance, ATOM problem is profoundly challenging due to the hardness of estimating user opinion in a multi-round campaign. Moreover, the process of opinion estimation and influence propagation intertwine with each other, which requires the model to consider the two components collectively. We propose an active learning framework called CONE (aCtive OpinioN Estimator) to address above challenges. Experimental results on two real-world datasets demonstrate that CONE improves the total opinion spread in a social network.
- N. Barbieri, F. Bonchi, and G. Manco . 2012. Topic-Aware Social Influence Propagation Models. ICDM '12. 81--90. Google ScholarDigital Library
- W. Chen, A. Collins, R. Cummings, T. Ke, Z. Liu, D. Rincon, X. Sun, Y. Wang, W. Wei, and Y. Yuan . 2011. Influence maximization in social networks when negative opinions may emerge and propagate SDM '11. 379--390.Google Scholar
- W. Chen, C. Wang, and Y. Wang . 2010. Scalable influence maximization for prevalent viral marketing in large-scale social networks KDD '10. 1029--1038. Google ScholarDigital Library
- P. Domingos and M. Richardson . 2001. Mining the network value of customers. In KDD '01. 57--66. Google ScholarDigital Library
- A. Gionis, E. Terzi, and P. Tsaparas . 2013. Opinion maximization in social networks. In SDM '13. 387--395.Google ScholarCross Ref
- A. Goyal, F. Bonchi, and L. Lakshmanan . 2011. A data-based approach to social influence maximization VLDB'11, Vol. Vol. 5. 73--84. Google ScholarDigital Library
- G. Guo, J. Zhang, D. Thalmann, and N. Yorke-Smith . 2014. ETAF: An Extended Trust Antecedents Framework for Trust Prediction ASONAM '14. Google ScholarDigital Library
- H. Hung, H. Shuai, D. Yang, L. Huang, W. Lee, J.Pei, and M. Chen . 2016. When Social Influence Meets Item Inference. In KDD '16. 915--924. Google ScholarDigital Library
- M. Jamali and M. Ester . 2010. A matrix factorization technique with trust propagation for recommendation in social networks. In RecSys '10. 135--142. Google ScholarDigital Library
- D. Kempe, J. Kleinberg, and É. Tardos . 2003. Maximizing the spread of influence through a social network KDD '03. 137--146. Google ScholarDigital Library
- Y. Koren . 2009. Collaborative filtering with temporal dynamics. In KDD '09. 447--456. Google ScholarDigital Library
- Y. Koren, R. Bell, and C. Volinsky . 2009. Matrix factorization techniques for recommender systems. Computer, Vol. 42, 8 (2009). Google ScholarDigital Library
- S. Lin, S-D. Lin, and M. Chen . 2015. A learning-based framework to handle multi-round multi-party influence maximization on social networks. In KDD '15. 695--704. Google ScholarDigital Library
- X. Liu, C. Aggarwal, Y. Li, X. Kong, X. Sun, and S. Sathe . 2016. Kernelized matrix factorization for collaborative filtering SDM '16. 378--386.Google Scholar
- X. Liu, Y. Song, C. Aggarwal, Y. Zhang, and X. Kong . 2017. BiCycle: Item Recommedation with Life Cycles. In ICDM '17. 297--306.Google Scholar
- B. Sarwar, G. Karypis, J. Konstan, and J. Riedl . 2001. Item-based collaborative filtering recommendation algorithms WWW '01. 285--295. Google ScholarDigital Library
- M. Solomon . 2014. Consumer behavior: Buying, having, and being. Vol. Vol. 10. Prentice Hall Engelwood Cliffs, NJ.Google Scholar
- X. Song, Y. Chi, K. Hino, and B. Tseng . 2007. Information flow modeling based on diffusion rate for prediction and ranking WWW '07. 191--200. Google ScholarDigital Library
- J. Sun and J. Tang . 2011. A survey of models and algorithms for social influence analysis. Social Network Data Analytics. Springer, 177--214.Google Scholar
- J. Tang, J. Sun, C. Wang, and Z. Yang . 2009. Social influence analysis in large-scale networks. KDD '09. 807--816. Google ScholarDigital Library
- S. Wasserman and K. Faust . 1994. Social network analysis: Methods and applications. Vol. Vol. 8. Cambridge University Press.Google Scholar
- B. Yang, Y. Lei, D. Liu, and J. Liu . 2013. Social collaborative filtering by trust. In IJCAI '13. 2747--2753. Google ScholarDigital Library
- H. Zhang, T. Dinh, and M. Thai . 2013. Maximizing the spread of positive influence in online social networks ICDCS'13. 317--326. Google ScholarDigital Library
- J. Zhang, S. Wang, Q. Zhan, and P. Yu. . 2016. Intertwined Viral Marketing in Social Networks. In ASONAM '16. Google ScholarDigital Library
- K. Zhou, S. Yang, and H. Zha . 2011. Functional matrix factorizations for cold-start recommendation SIGIR '11. 315--324. Google ScholarDigital Library
Index Terms
Active Opinion Maximization in Social Networks
Recommendations
Topic-constrained influence maximization in social networks
ICCIP '17: Proceedings of the 3rd International Conference on Communication and Information ProcessingUnderstanding the spread of influence and maximizing it through online social networks lead to gain a lot of benefits for various practical applications such as viral marketing, personalized recommendation, cascade detection, and information monitoring. ...
Opinion Maximization in Signed Social Networks Using Centrality Measures and Clustering Techniques
Distributed Computing and Intelligent TechnologyAbstractIn a social network, Opinion Maximization is a problem that targets spreading the desired opinion across the social network. In the real world, every user/individual has their own opinion. The opinion of an individual can be favorable or ...
Viral Opinion Spreading Model in Social Networks
SOCIALCOM '13: Proceedings of the 2013 International Conference on Social ComputingWe proposed a new model, which capture the main difference between information and opinion spreading. In information spreading additional exposure to certain information has a small effect. Contrary, when an actor is exposed to 2 opinioned actors the ...
Comments