Social Network Analysis and Mining

, Volume 3, Issue 4, pp 1433–1447 | Cite as

Spectral clustering for link prediction in social networks with positive and negative links

Original Article


Online social networks (OSNs) recommend new friends to registered users based on local features of the graph (i.e. based on the number of common friends that two users share). Real OSNs (e.g. Facebook) do not exploit all network structure. Instead, they consider only pathways of maximum length 2 between a user and his candidate friends. This can limit the accuracy of prediction. On the other hand, there are global approaches, which detect the overall path structure in a network, being computationally prohibitive for huge-size social networks. In this paper, we provide friend recommendations, by performing multi-way spectral clustering, which uses information obtained from the top few eigenvectors and eigenvalues of the normalized Laplacian matrix and computes a multi-way partition of the data. As a result, it produces a less noisy matrix, which is smaller and more compact than the original one, focusing on main linking trends of the social network. Thus, we are able to provide fast and more accurate friend recommendations. Moreover, spectral clustering compared to traditional clustering algorithms, such as k-means and DBSCAN, which assume globular (convex) regions in Euclidean space, is more flexible, in capturing the non-connected components of a social graph and a wider range of cluster geometries. We perform an extensive experimental comparison of the proposed method against existing link prediction algorithms, the k-means and two-way nCut clustering algorithms, using synthetic and three real data sets (Hi5, Facebook, and Epinions). Our experimental results show that our SpectralLink algorithm outperforms the local approaches, the k-means and two-way nCut clustering algorithms in terms of effectiveness, whereas it is more efficient than the global approaches. We show that a significant accuracy improvement can be gained by using information about both positive and negative edges.


  1. Abbassi Z, Mirrokni VS (2007) A recommender system based on local random walks and spectral methods. In: Workshop on knowledge discovery on the web (WebKDD’2007) in conjuction with the 1st international workshop on social networks analysis (SNA-KDD 2007), pp 139–153Google Scholar
  2. Adamic L, Adar E (2005) How to search a social network. Soc Netw 27(3):187–203CrossRefGoogle Scholar
  3. Agarwal V, Bharadwaj KA (2013) collaborative filtering framework for friends recommendation in social networks based on interaction intensity and adaptive user similarity. Soc Netw Anal Mining (to appear)Google Scholar
  4. Al Hasan M, Chaoji V, Salem S, Zaki M (2006) Link prediction using supervised learning. In: SDM06: workshop on link analysis, counter-terrorism and securityGoogle Scholar
  5. Caci B, Cardaci M, Tabacchi M (2011) Facebook as a small world: a topological hypothesis. Soc Netw Anal MiningGoogle Scholar
  6. Chen J, Geyer W, Dugan C, Muller M, Guy I (2009) Make new friends, but keep the old: recommending people on social networking sites. In: CHI ’09: Proceedings of the 27th international conference on Human factors in computing systems, pp 201–210Google Scholar
  7. Clauset A, Moore C, Newman ME (2008) Hierarchical structure and the prediction of missing links in networks. Nature 453(7191):98–101CrossRefGoogle Scholar
  8. Costa L, Rodrigues F, Travieso G, Boas P (2007) Characterization of complex networks: a survey of measurements. Adv Phys 56(1):167–242CrossRefGoogle Scholar
  9. Davis D, Lichtenwalter R, Chawla N (2013) Supervised methods for multi-relational link prediction. Soc Netw Anal Mining (to appear)Google Scholar
  10. Fazel-Zarandi M, Devlin H, Huang Y, Contractor N (2011) Expert recommendation based on social drivers, social network analysis, and semantic data representation. In: Proceedings of the 2nd international workshop on information heterogeneity and fusion in recommender systems. ACM, New York, pp 41–48Google Scholar
  11. Fouss F, Francoisse K, Yen L, Pirotte A, Saerens M (2009) An experimental investigation of graph kernels on collaborative recommendation and semisupervised classification. Technical ReportGoogle Scholar
  12. Fouss F, Pirotte A, Renders JM, Saerens M (2007) Random-walk computation of similarities between nodes of a graph with application to collaborative recommendation. IEEE Trans Knowl Data Eng 19(3):355–369CrossRefGoogle Scholar
  13. Golub G, Van Loan C (1983) Matrix computations. Johns Hopkins studies in mathematical sciencesGoogle Scholar
  14. Guy I, Ronen I, Wilcox E (2009) Do you know? Recommending people to invite into your social network. In: IUI ’09: Proceedings of the 13th international conference on intelligent user interfaces, pp 77–86Google Scholar
  15. Hage P, Harary F (1983) Structural models in anthropology 56Google Scholar
  16. Higham H, Kalna G, Kibble M (2007) Spectral clustering and its use in bioinformatics. J Comput Appl Math 204(1)Google Scholar
  17. Hou Y (2005) Bounds for the least Laplacian eigenvalue of a signed graph. Acta Math Sinica 21:955–960CrossRefMATHGoogle Scholar
  18. Iakovidou N, Symeonidis P, Manolopoulos Y (2010) Multiway spectral clustering link prediction in protein–protein interaction networks. In: 10th IEEE international conference on information technology and applications in biomedicine (ITAB). IEEE, New York, pp 1–4Google Scholar
  19. Jeh G, Widom J (2002) Simrank: a measure of structural-context similarity. In: KDD ’02: proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 538–543Google Scholar
  20. Katz L (1953) A new status index derived from sociometric analysis. Psychometrika 18(1):39–43CrossRefMATHGoogle Scholar
  21. Kunegis J, Lommatzsch A (2009) Learning spectral graph transformations for link prediction. Proc Int Conf Machine LearnGoogle Scholar
  22. Leskovec J, Huttenlocher D, Kleinberg J (2010a) Predicting positive and negative links in online social networks. In: Proceedings 19th international conference on World Wide Web (WWW’2010), Raleigh, NC, pp 641–650Google Scholar
  23. Leskovec J, Huttenlocher D, Kleinberg J (2010b) Signed networks in social media. In: Proceedings of the 28th international conference on human factors in computing systems. ACM, New York, pp 1361–1370Google Scholar
  24. Liben-Nowell D, Kleinberg J (2003) The link prediction problem for social networks. In: Proceedings of the 12th international conference on information and knowledge management (CIKM)Google Scholar
  25. Liben-Nowell L, Kleinberg J (2007) The link-prediction problem for social networks. J Am Soc Inf Sci Technol (JASIST) 58(7):1019–1031CrossRefGoogle Scholar
  26. Lo S, Lin C (2006) Wmr: a graph-based algorithm for friend recommendation. In: Proceedings of the IEEE/ACM international conference on web intelligence (WIC), Hong Kong, China, pp 121–128Google Scholar
  27. Lü L, Zhou T (2011) Link prediction in complex networks: a survey. Phys A 390(6):1150–1170CrossRefGoogle Scholar
  28. Maila M, Shi J (2001) A random walks view of spectral segmentation. In: International conference on AI and statistics (AISTAT)Google Scholar
  29. Ng A, Jordan M, Weiss Y (2001) On spectral clustering: analysis and an algorithm. Adv Neural Inf Process Syst 14:849–856Google Scholar
  30. Pan J, Yang H, Faloutsos C, Duygulu P (2004) Automatic multimedia cross-modal correlation discovery. In: KDD ’04: proceedings of the 10th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 653–658Google Scholar
  31. Papadimitriou A, Symeonidis P, Manolopoulos Y (2011) Friendlink: link prediction in social networks via bounded local path traversal. In: 2011 International conference on computational aspects of social networks (CASoN). IEEE, New York, pp 66–71Google Scholar
  32. Rattigan M, Jensen D (2005) The case for anomalous link discovery. SIGKDD Explor 7(2):41–47CrossRefGoogle Scholar
  33. Shi J and Malik J. (1997) Normalized cuts and image segmentation. In CVPR ’97: Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR ’97), page 731Google Scholar
  34. Symeonidis P, Tiakas E, and Manolopoulos Y (2010) Transitive node similarity for link prediction in social networks with positive and negative links. In Proceedings of the 4th International Conference on Recommender Systems (RecSys’2010), Barcelon, Spain, pp 183–190Google Scholar
  35. Tong H, Faloutsos C, Pan J (2006) Fast random walk with restart and its applications. In: ICDM ’06: proceedings of the 6th international conference on data mining. IEEE Computer Society, New York, pp 613–622Google Scholar
  36. Tsourakakis C, Drineas P, Michelakis E, Koutis I, Faloutsos C (2011) Spectral counting of triangles via element-wise sparsification and triangle-based link recommendation. Soc Netw Anal Mining 1(2):75–81CrossRefGoogle Scholar
  37. Yan D, Huang L, Jordan M (2009) Fast approximate spectral clustering. In: KDD ’09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 907–916Google Scholar

Copyright information

© Springer-Verlag Wien 2013

Authors and Affiliations

  1. 1.Department of InformaticsAristotle UniversityThessalonikiGreece

Personalised recommendations