A novel approach to online social influence maximization

Original Article

Abstract

Online social networks are becoming a true growth point of Internet. As individuals constantly desire to interact with each other, the ability for Internet to deliver this networking influence becomes much stronger. In this paper, we study the online social influence maximization problem, which is to find a small group of influential users that maximizes the spread of influence through networks. After a thorough analysis of existing models, especially two classical ones, namely Independent cascade and linear thresholds, we argue that their idea that each user can only be activated by its active neighbors is not applicable to online social networks, since in many applications there is no clear concept for the issue of "activation". In our proposed influence model, if there is a social influence path linking two nonadjacent individuals, the value of influence between these two individuals can be evaluated along the existing social path based on the influence transitivity property under certain constraints. To compute influence probabilities between two neighbors, we also develop a new method which leverages both structure of networks and historical data. With reasonably learned influence probabilities, we recast the problem of online influence maximization to a weighted maximum cut problem which analyzes the influence flow among graph vertices. By running a semidefinite program-based (GW) algorithm on a complete influence graph, an optimal seed set can be identified effectively. We also provide experimental results on real online social networks, showing that our algorithm significantly outperforms greedy methods.

References

  1. Akcora CG, Carminati B, Ferrari E (2011) Network and profile based measures for user similarities on social networks. In: IEEE international conference on information reuse and integration (IRI), pp 292–298Google Scholar
  2. Albert R, Jeong H, Barabasi A (2000) Error and attack tolenrance of complex networks. Nature 406:378–382CrossRefGoogle Scholar
  3. Alizadeh F (1995) Interior point methods in semidefinite programming with applications to combinatorial optimization. SIAM J Optim 5:13–51CrossRefMathSciNetMATHGoogle Scholar
  4. Aral S (2011) Identifying social influence: a Comment on opinion leadership and social contagion in new product diffusion. Mark Sci 30(2)217–223CrossRefGoogle Scholar
  5. Bakshy E et al (2011) Everyones an influencer: quantifying influence on Twitter. In: WSDM, pp 65–74Google Scholar
  6. Bhagat S, Goyal A, Lakshmanan LVS (2012) Maximizing product adoption in social networks. In: WSDM, pp 603–612Google Scholar
  7. Bross J, Richly K, Kohnen M, Meinel C (2012) Identifying the top-dogs of the blogosphere. Soc Netw Analy Min 2(1):53–67CrossRefGoogle Scholar
  8. Burer S, Monteiro R (2004) Local minima and convergence in low-rank semidefinite programming. Math Progr 103(3):427–444CrossRefMathSciNetGoogle Scholar
  9. Chen W, Wang C, Wang Y (2010a) Scalable influence maximization for prevalent viral marketing in large-scale social networks. In: KDD, pp 1029–1038Google Scholar
  10. Chen W, Yuan Y, Zhang L (2010b) Scalable influence maximization in social networks under the linear threshold model. In: ICDM, pp 88–97Google Scholar
  11. Christianson B, Harbison WS (1996) Why isnt trust transitivie? In: International workshop on security protocols, pp 171–176Google Scholar
  12. Domingos P, Richardson M (2001) Mining the network value of customers. In: Proceedings of the 7th ACM SIGKDD conference on knowledge discovery and data mining, pp 57–66Google Scholar
  13. Ferri F, Grifoni P, Guzzo T (2012) New forms of social and professional digital relationships: the case of Facebook. Soc Netw Analy Mini 2(2):121–137CrossRefGoogle Scholar
  14. Gimpel J, Karnes K, Mctague J, Pearson-Merkowitz S (2008) Distance-decay in the political geography of friends-and-neighbors voting. Polit Geogr 27:231–252CrossRefGoogle Scholar
  15. Goemans MX, Williamson DP (1995) Improved approximation algorithms for maximum cut and satisfiability using semidefinite programming. J ACM, 42(6):1145CrossRefMathSciNetGoogle Scholar
  16. Goyal A, Bonchi F, Lakshmanan LVS (2010) Learning influence probabilities in social networks. In: WSDM, pp 241–250Google Scholar
  17. Goyal A, Lu W, Lakshmanan LVS (2011) A data-based approach to social influence maximization. In: PVLDB, vol 5, no 1Google Scholar
  18. Guha R, Kumar R, Raghavan P, Tomkins A (2004) Propagation of trust and distrust. In: WWW, pp 403–412Google Scholar
  19. Hang C, Wang Y, Singh M (2009) Operators for propagating trust and their evaluation in social networks. In: AAMAS, pp 1025–1032Google Scholar
  20. Ienco D, Bonchi F, Castillo C (2010) The meme ranking problem: maximizing microblogging virality. In: SIASP workshop of ICDM, pp 328–335Google Scholar
  21. Iyengar R, Van den Bulte C, Valente TW (2011) Opinion leadership and social contagion in new product diffusion. Mark Sci 30(2):195–212CrossRefGoogle Scholar
  22. Jamali M, Ester M (2010) A matrix factorization technique with trust propagation for recommendation in social networks. In: RecSys, pp 135–142Google Scholar
  23. Jin Y, Lin CY, Matsuo Y, Ishizuka M (2012) Mining dynamic social networks from public news articles for company value prediction. Soc Netw Anal Min 2(3):217–228CrossRefGoogle Scholar
  24. Josang A, Pope S.: (2005) Semantic constraints for trust transitivity. In: APCCM, pp 59–68Google Scholar
  25. Kempe D, Kleinberg JM, Tardos E (2003) Maximizing the spread of influence through a social network. In: Proceedings of the 9th ACM SIGKDD conference on knowledge discovery and data mining, pp 137–146Google Scholar
  26. Kimura M, Saito K (2006) Tractable models for information diffusion in social networks. In: Proceedings of the 10th European conference on principles and practice of knowledge discovery in databases, pp 259–271Google Scholar
  27. Lappas T, Terzi E, Gunopulos D, Mannila H (2010) Finding effectors in social networks. In: KDD, pp 1059–1068Google Scholar
  28. Leskovec J, Krause A, Guestrin C, Faloutsos C, Van-Briesen J, Glance NS (2007) Cost-effective outbreak detection in networks. In: Proceedings of the 13th ACM SIGKDD conference on knowledge discovery and data mining, pp 420–429Google Scholar
  29. Leskovec J, Adamic LA, Huberman BA (2007) The dynamics of viral marketing. ACM Trans Web (TWEB) 1(1):5CrossRefGoogle Scholar
  30. Li L, Wang Y, Lim E (2009) Trust-oriented composite services selection and discovery. In: ICSOC, pp 50–67Google Scholar
  31. Ma H, King I, Lyu MR (2007) Effective missing data prediction for collaborative filtering. In: Proceedings of the 30th annual international ACM SIGIR conference on research and development in information retrieval, USA, pp 39–46Google Scholar
  32. Mathioudakis M, Bonchi F, Castillo C, Gionis A, Ukkonen A (2011) Sparsification of influence networks. In: KDD, pp 529–537Google Scholar
  33. Nail J (2004) The consumer advertising backlash. In: Forrester research and intelliseek market research reportGoogle Scholar
  34. Richardson M, Domingos P (2002) Mining knowledge-sharing sites for viral marketing. In: Proceedings of the eighth ACM SIGKDD international conference on knowledge discovery and data mining, pp 61–70Google Scholar
  35. Saito K et al (2008) Prediction of information diffusion probabilities for independent cascade model. In: KES, pp 67–75Google Scholar
  36. Song X, Chi Y, Hino K, Tseng BL (2007) Information flow modeling based on diffusion rate for prediction and ranking. In: WWW, pp 191–200Google Scholar
  37. Walter F, Battiston S, Schweitzer F (2008) A model of a trust-based recommendation system on a social network. AAMAS 16(1):57–74Google Scholar
  38. Wasserman S, Faust K (1994) Social network analysis. Cambridge university Press, CambridgeCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 2014

Authors and Affiliations

  1. 1.Erik Jonsson School of Engineering and Computer ScienceUniversity of Texas at Dallas RichardsonUSA

Personalised recommendations