Skip to main content
SpringerLink
Log in

Statistical mechanics approach for collaborative business social network reconstruction

  • Original Article
  • Published:
Social Network Analysis and Mining Aims and scope Submit manuscript

Abstract

The role of human resources has become a key factor for the success of an organization. Based on a research collaboration with an aeronautical company, the paper compares two different approaches for the reconstruction of a collaborative social network in the business realm. Traditional social network analysis and novel statistical inference models were both evaluated against data provided by the company, with the final scope of scouting key employees in the network, as well as exploiting the knowledge-transfer processes. As a main outcome of this paper, it was found how the network reconstruction using statistical models has an increased robustness, as well as sensitivity, allowing to discover hidden correlations among the users.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Notes

  1. See Sect. 5.1.

  2. Adopted elsewhere in cited works of SNA literature for the same task.

  3. This makes it intrinsically more robust than the Bethe approximation, where convergence and uniqueness of the solution are not guaranteed, even if TRW is often outperformed in practical tasks.

  4. See Sect. 5.1.

  5. An add-in to the Microsoft Excel 2007 spreadsheet software (http://nodexl.codeplex.com).

  6. To be intended as those dummy states, associated to inactive users, who are not performing any specific activity when a network observation occurs.

  7. Assuming a single user cannot perform more than one activity at once.

  8. And in particular, it is unknown which nodes in the interaction model E are truly linked to each other, i.e. have a non-negligible interaction: \((i,j) \in E \; \iff \; H_{(i,j).} \,\ncong\, 0\).

  9. And this is indeed the case for the data available in our study, as better explained in the next paragraph.

  10. Specifically, both 1M and 500k realizations were computed.

  11. Preserving more links, indeed, leads to the discovery of weak interactions.

References

  • Bisconti C, Corallo A, Fortunato L, Gentile AA, Massafra A, Pell P (2015) Reconstruction of a real world social network using the Potts model and Loopy Belief Propagation. Front Psychol 6:1698

    Article  Google Scholar 

  • Bordogna CM, Albano EV (2007) Dynamic behavior of a social model for opinion formation. Phys Rev E 76(6):061125

    Article  Google Scholar 

  • Borgatti SP (2012) Social network analysis, two-mode concepts in. In: Computational complexity, Springer, New York, pp 2912–2924

  • Braunstein A, Pagnani A, Weigt M, Zecchina R (2008) Gene-network inference by message passing. J Phys Conf Ser 95:012016

    Article  Google Scholar 

  • Burt RS (1992) Structural holes. Harvard University Press, Cambridge

    Google Scholar 

  • Busch P, Fettke P (2011) Business process management under the microscope: the potential of social network analysis. In: Proceedings of the 44th Hawaii international conference on system sciences

  • Chan K, Liebowitz J (2006) The synergy of social network analysis and knowledge mapping: a case study. Int J Manag Decis Mak 7(1):19–35

    Google Scholar 

  • Cocco S, Monasson R (2011) Adaptive cluster expansion for inferring Boltzmann machines with noisy data. Phys Rev Lett 106:090601

    Article  Google Scholar 

  • Cross R, Parker A (2001) Knowing what we know: supporting knowledge creation and sharing in social networks. Organ Dyn

  • Cross R, Parker A (2002) Making invisible work visible: using social network analysis to support strategic collaboration. Calif Manag Rev 44(2):25–46

    Article  Google Scholar 

  • Cross R, Prusak L (2002) The people who make organizations go-or stop. Harv Bus Rev 80(6):104–112

    Google Scholar 

  • Daudin J-J, Picard F, Robin S (2008) A mixture model for randomgraphs. Stat Comput 18:173–183

    Article  MathSciNet  Google Scholar 

  • dos Santos TA, de Araujo RM, Magdaleno AM (2010) Identifying collaboration patterns in software development social networks. INFOCOMP J Comput Sci 51–60

  • Drucker PF (1999) Management: tasks, responsibilities. Addison-Wesley, Harlow

    Google Scholar 

  • Ekeberg M, Lvkvist C, Lan Y, Weigt M, Aurell E (2013) Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models. Phys Rev E 87:012707

    Article  Google Scholar 

  • Fettke P (2009) How Conceptual Modeling is Used. Commun Assoc Inf Syst 25(1):43

    Google Scholar 

  • Hammer M, Champy J (1993) Re-engineering the corporation, a manifesto for business revolution. Harper Business, New York

    Google Scholar 

  • Hanneman RA, Riddle M (2005) Introduction to social network methods. University of California, Riverside

  • Heskes T (2004) On the uniqueness of loopy belief propagation fixed points. Neural Comput 16:2379–2413

    Article  MATH  Google Scholar 

  • Horiguchi T (1981) On the Bethe approximation for the random bond Ising model. Physica A 107:360–370. doi:10.1016/0378-4371(81)90095-9

    Article  MathSciNet  Google Scholar 

  • http://nodexl.codeplex.com (2014).12.03

  • Jedidi K, Jagpal HS, DeSarbo WS (1997) Finite-mixture structural equation models for response-based segmentation and unobserved heterogeneity. Mark Sci 16:39–59

    Article  MATH  Google Scholar 

  • Kiwata H (2012) Physical consideration of an image in image restoration using Bayes formula. Phys A 391:2215–2224

    Article  MathSciNet  Google Scholar 

  • Kolmogorov V (2006) Convergent tree-reweighted message passing for energy minimization. Pattern Anal Mach Intell (IEEE) 28:1568–1583

    Article  Google Scholar 

  • Koschmider A, Song M, Reijers HA (2009) Social software for modeling business processes. In: BPM 2008 workshops. LNBIP, vol 17, pp 642–653

  • Liu S, Ying L, Shakkottai S (2010) Influence maximization in social networks: an Ising-model-based approach, communication, control, and computing (Allerton). In: 48th annual Allerton conference on (IEEE), pp 570–576

  • Mooij JM (2011) Uniqueness of belief propagation on signed graphs. In: Advances in neural information processing systems, pp 1521–1529

  • Mooij JM (2010) libDAI: a free and open source C++ library for discrete approximate inference in graphical models. J Mach Learn Res 11:2169–2173

    MATH  Google Scholar 

  • Newman ME, Leicht EA (2007) Mixture models and exploratory analysis in networks. Proc Natl Acad Sci USA 104:9564–9569

    Article  MATH  Google Scholar 

  • Nowicki K, Snijders TAB (2001) Estimation and prediction for stochastic blockstructures. J Am Stat Assoc 96:1077–1087

    Article  MathSciNet  MATH  Google Scholar 

  • Pajevic S, Plenz D (2009) Efficient network reconstruction from dynamical cascades identifies small-world topology of neuronal avalanches. PloS Comput Biol 5:e1000271

    Article  MathSciNet  Google Scholar 

  • Papazoglou MP (2003) Web services and business transactions. World Wide Web Internet Web Inf Syst 6:49–91

    Article  Google Scholar 

  • Phan D, Gordon MB, Nadal JP (2004) 20 social interactions in economic theory: an insight from statistical mechanics. In: Cognitive economics: an interdisciplinary approach, Springer, Berlin, pp 355–358

  • Ricci-Tersenghi F (2012) The Bethe approximation for solving the inverse Ising problem: a comparison with other inference methods. J Stat Mech Theory Exp 8:P08015

    Google Scholar 

  • Scheer A-W (2001) ARIS-modellierungsmethoden, metamodelle,anwendungen (ARIS-modeling methods, meta-models, applications). Springer, Berlin

    Book  Google Scholar 

  • Serrats O (2009) Social network analysis, Knowledge Solutions Asian Development Bank

  • Sessak V, Monasson R (2009) Small-correlation expansions for the inverse Ising problem. J Phys A Math Theor 42:055001

    Article  MathSciNet  MATH  Google Scholar 

  • Song M, Choi I, Kim K, van der Aalst WMP (2008) Deriving social relations among organizational units from process models. Technische Universiteit Eindhoven, Eindhoven

    Google Scholar 

  • Tanaka K, Inoue J, Titterington DM (2003) Probabilistic image processing by means of Bethe approximation for Q-Ising model. J Phys A Math Gen 36(43):11023–11036

    Article  MathSciNet  MATH  Google Scholar 

  • Valiant LG (1979) The complexity of computing the permanent. Theor Comput Sci 8:189–201

    Article  MathSciNet  MATH  Google Scholar 

  • van der Aalst W (2005) Business alignment: using process mining as a tool for Delta analysis and conformance testing. Requir Eng 10:198–211

    Article  Google Scholar 

  • van der Aalst W, Reijers H (2005) Discovering social networks from event logs. Comput Support Coop Work 14:549–593

    Article  Google Scholar 

  • van der Aalst W, Reijers H (2007) Business process mining: an industrial application. Inf Syst 32:713–732

    Article  Google Scholar 

  • Wakita K, Tsurumi T (2007) Finding community structure in mega-scale social networks. In: Proceedings of the 16th international conference on World Wide Web, ACM, pp 1275–1276

  • Weller A, Tang K, Sontag D, Jebara T (2014) Understanding the Bethe approximation: when and how can it go wrong. In: Uncertainty in Artificial Intelligence (UAI)

  • Yamanishi Y, Vert J-P, Kanehisa M (2004) Protein network inference from multiple genomic data: a supervised approach. Bioinformatics 20:363–370

    Article  Google Scholar 

  • Yasuda M, Kataoka S, Tanaka K (2012) Inverse problem in pairwise Markov random fields using loopy belief propagation. J Phys Soc Jpn 81(4):044801–044808

    Article  Google Scholar 

  • Yeung MKS, Tegne J, Collins JJ (2002) Reverse engineering gene networks using singular value decomposition and robust regression. Proc Natl Acad Sci 99:6163–6168

    Article  Google Scholar 

  • Zeng H-L, Aurell E, Alava M, Mahmoudi H (2011) Network inference using asynchronously updated kinetic Ising model. Phys Rev E 83:041135

    Article  Google Scholar 

Download references

Acknowledgments

We thank Emanuele Rizzo for his expert technical help and Marianovella Mello for her administrative work. This work was part of the Project MUSCA (PAC02L1-0018), funded by the Italian Ministry of Education, University and Research.

Author information

Authors and Affiliations

  1. Department of Innovation Engineering, University of Salento, Lecce, Italy

    Angelo Corallo, Cristian Bisconti & Laura Fortunato

  2. Centre for Nanoscience and Quantum Information, University of Bristol, Bristol, UK

    Antonio Andrea Gentile

  3. Dhitech SCARL, High Technology Cluster, Lecce, Italy

    Antonio Andrea Gentile & Piergiuseppe Pellè

Authors
  1. Angelo Corallo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Cristian Bisconti
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Laura Fortunato
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Antonio Andrea Gentile
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Piergiuseppe Pellè
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Cristian Bisconti.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Corallo, A., Bisconti, C., Fortunato, L. et al. Statistical mechanics approach for collaborative business social network reconstruction. Soc. Netw. Anal. Min. 6, 35 (2016). https://doi.org/10.1007/s13278-016-0342-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13278-016-0342-0

Keywords

Search

Navigation