Skip to main content
SpringerLink
Log in

Automatic role identification for research teams with ranking multi-view machines

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

Research teams have been well recognized as the norm in modern scientific discovery. Rather than a loose collection of researchers, a well-performing research team is composed of a number of researchers, each of them playing a particular role (i.e., principal investigator, sub-investigator or research staff) for a short- or long-term effort. Role analysis for research teams would help gain insights into the dynamics of teams and the behavior of their members. In this paper, we address the problem of research role identification for large research institutes in which similar yet separated teams coexist. In particular, we represent a research team as teamwork networks and generate the feature representation of each member using a number of network metrics. Afterward, we propose RankMVM, short for Ranking Multi-View Machines, to learn the role identification model. Compared with traditional predictive models, RankMVM is advantageous in exploring high-order feature interactions in an efficient way, as well as handling the specific challenges of the research role identification task, including partially ordered learning targets and sparse feature interactions. In the experiments, we assess the performance on a real-world research team dataset. Extensive experimental evaluations verify the advantages of our proposed research role identification approach.

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. One may argue that the ranking formulation introduces an additional hyperparameter k. Actually, such hyperparameters are also required in classification approaches to obtain determinate role labels. For example, if the task is formulated as a 3-class classification and approached using OneVsAll decomposition strategy, the rough outputs of the three classifiers (PI/All, SI/All, RS/All) are usually in different scales and thus post-processing that generally involves additional hyperparameters (e.g., thresholds of each class) is needed to obtain the final labels. Therefore, the ranking formulation does not have the disadvantage of requiring more hyperparameter-tuning compared with the classification formulation.

  2. Note that this vanishing gradient problem bears a certain resemblance to that incurred when learning deep neural networks: the chain rule of gradient computation is achieved by multiplying the gradients of each layer which range in (0, 1) if the common sigmoid/tanh activation functions are used, thus the gradient decreases exponentially with the number of layers.

  3. http://npd.nsfc.gov.cn.

  4. Note that the role information cannot be leveraged in the construction of the network. In this experiment, the aim is to compare the network embedding features with the manually crafted ones, both generated in an unsupervised manner.

References

  1. Abnar A, Takaffoli M, Rabbany R et al (2015) SSRM: structural social role mining for dynamic social networks. Soc Netw Anal Min 5(1):56

    Article  Google Scholar 

  2. Alves BL, Benevenuto F, Laender AH (2013) The role of research leaders on the evolution of scientific communities. In: Proceedings of the 22nd ACM international conference on world wide web, pp 649–656

  3. Brandes U, Lerner J (2010) Structural similarity: spectral methods for relaxed blockmodeling. J Classif 27(3):279–306

    Article  MathSciNet  MATH  Google Scholar 

  4. Bucak SS, Mallapragada PK, Jin R et al (2009) Efficient multi-label ranking for multi-class learning: application to object recognition. In: 2009 IEEE 12th international conference on computer vision, IEEE, pp 2098–2105

  5. Burges C, Svore K, Bennett P et al (2011) Learning to rank using an ensemble of lambda-gradient models. In: Proceedings of the learning to rank challenge, pp 25–35

  6. Can EF, Manmatha R (2013) Formulating action recognition as a ranking problem. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 251–256

  7. Cao H, Verma R, Nenkova A (2015) Speaker-sensitive emotion recognition via ranking: studies on acted and spontaneous speech. Comput Speech Lang 29(1):186–202

    Article  Google Scholar 

  8. Cao Y, Xu J, Liu TY, et al (2006) Adapting ranking svm to document retrieval. In: Proceedings of the 29th ACM international conference on Research and development in information retrieval, pp 186–193

  9. Cao B, Zheng L, Zhang C et al (2017) Deepmood: modeling mobile phone typing dynamics for mood detection. In: Proceedings of the 23rd ACM international conference on knowledge discovery and data mining, pp 747–755

  10. Cao B, Zhou H, Li G et al (2016) Multi-view machines. In: Proceedings of the 9th ACM international conference on web search and data mining, pp 427–436

  11. Cheng Y, Agrawal A, Choudhary A et al (2014) Social role identification via dual uncertainty minimization regularization. In: Proceedings of the 14th IEEE international conference on data mining, pp 767–772

  12. Cruz R, Fernandes K, Cardoso JS et al (2016) Tackling class imbalance with ranking. In: 2016 International joint conference on neural networks (IJCNN), IEEE, pp 2182–2187

  13. da Costa JFP, Alonso H, Cardoso JS (2008) The unimodal model for the classification of ordinal data. Neural Netw 21(1):78–91

    Article  MATH  Google Scholar 

  14. Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12(7):257–269

    MathSciNet  MATH  Google Scholar 

  15. Ertekin Ş, Rudin C (2011) On equivalence relationships between classification and ranking algorithms. J Mach Learn Res 12(Oct):2905–2929

    MathSciNet  MATH  Google Scholar 

  16. Estrada E, Hatano N (2008) Communicability in complex networks. Phys Rev E 77(3):036111

    Article  MathSciNet  Google Scholar 

  17. Freeman LC (1978) Centrality in social networks conceptual clarification. Soc Netw 1(3):215–239

    Article  Google Scholar 

  18. Gilpin S, Eliassi-Rad T, Davidson I (2013) Guided learning for role discovery (GLRD): framework, algorithms, and applications. In: Proceedings of the 19th ACM international conference on knowledge discovery and data mining, pp 113–121

  19. Guo W, Wu S, Wang L et al (2016) Personalized ranking with pairwise factorization machines. Neurocomputing 214:191–200

    Article  Google Scholar 

  20. Gupte PV, Ravindran B, Parthasarathy S (2017) Role discovery in graphs using global features: Algorithms, applications and a novel evaluation strategy. In: Proceedings of the 33rd IEEE international conference on data engineering, pp 771–782

  21. Hall KL, Vogel AL, Huang GC et al (2018) The science of team science: a review of the empirical evidence and research gaps on collaboration in science. Am Psychol 73(4):532

    Article  Google Scholar 

  22. Henderson K, Gallagher B, Eliassi-Rad T et al (2012) Rolx: structural role extraction & mining in large graphs. In: Proceedings of the 18th ACM international conference on Knowledge discovery and data mining, pp 1231–1239

  23. Hu X, Liu H (2012) Social status and role analysis of palin’s email network. In: Proceedings of the 21st international conference on world wide web, pp 531–532

  24. Jiang X, Hu Y, Li H (2009) A ranking approach to keyphrase extraction. In: Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, pp 756–757

  25. Kate K, Ravindran B (2009) Epsilon equitable partition: a positional analysis method for large social networks. In: Proceedings of the international conference on management of data

  26. Katz L (1953) A new status index derived from sociometric analysis. Psychometrika 18(1):39–43

    Article  MATH  Google Scholar 

  27. Kazmi F, Butt WH, Saeed A (2018) Evaluation of role detection approaches in terrorist networks. In: Proceedings of the 2nd international conference on management engineering, software engineering and service sciences, pp 245–249

  28. Koschützki D, Lehmann KA, Peeters L et al (2005) Centrality indices. In: Network analysis, pp 16–61

  29. Lee H, Battle A, Raina R et al (2007) Efficient sparse coding algorithms. In: Advances in neural information processing systems, pp 801–808

  30. Lu CT, He L, Shao W et al (2017) Multilinear factorization machines for multi-task multi-view learning. In: Proceedings of the 10th ACM international conference on web search and data mining, pp 701–709

  31. Merton RK, Merton RK (1968) Social theory and social structure. Simon and Schuster, New York

    MATH  Google Scholar 

  32. Nagamochi H, Ibaraki T (2008) Algorithmic aspects of graph connectivity. Cambridge University Press, Cambridge

    Book  MATH  Google Scholar 

  33. Narasimhan H, Agarwal S (2013) On the relationship between binary classification, bipartite ranking, and binary class probability estimation. In: Advances in neural information processing systems, pp 2913–2921

  34. Nielsen F, Sun K (2016) Guaranteed bounds on information-theoretic measures of univariate mixtures using piecewise log-sum-exp inequalities. Entropy 18(12):442

    Article  MathSciNet  Google Scholar 

  35. Noldus R, Van Mieghem P (2015) Assortativity in complex networks. J Complex Netw 3(4):507–542

    Article  MathSciNet  MATH  Google Scholar 

  36. Nowicki K, Snijders TAB (2001) Estimation and prediction for stochastic blockstructures. J Am Stat Assoc 96(455):1077–1087

    Article  MathSciNet  MATH  Google Scholar 

  37. Page L, Brin S, Motwani R et al (1999) The pagerank citation ranking: bringing order to the web. Technical report, Stanford InfoLab

  38. Pei Y, Zhang J, Fletcher GH et al (2018) DyNMF: role analytics in dynamic social networks. In: Proceedings of the 27th international joint conferences on artificial intelligence, pp 3818–3824

  39. Rendle S, Freudenthaler C, Gantner Z et al (2009) BPR: Bayesian personalized ranking from implicit feedback. In: Proceedings of the 25th conference on uncertainty in artificial intelligence, pp 452–461

  40. Ribeiro LF, Saverese PH, Figueiredo DR (2017) struc2vec: Learning node representations from structural identity. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pp 385–394

  41. Rossi RA, Ahmed NK (2015) Role discovery in networks. IEEE Trans Knowl Data Eng 27(4):1112–1131

    Article  Google Scholar 

  42. Ruhnau B (2000) Eigenvector-centrality-a node-centrality? Soc Netw 22(4):357–365

    Article  Google Scholar 

  43. Saramäki J, Kivelä M, Onnela JP et al (2007) Generalizations of the clustering coefficient to weighted complex networks. Phys Rev E 75(2):027105

    Article  Google Scholar 

  44. Shalev-Shwartz S, Tewari A (2011) Stochastic methods for l1-regularized loss minimization. J Mach Learn Res 12(6):1865–1892

    MathSciNet  MATH  Google Scholar 

  45. Tang J, Qu M, Wang M, et al (2015) Line: large-scale information network embedding. In: Proceedings of the 24th international conference on world wide web, pp 1067–1077

  46. Tsitsulin A, Mottin D, Karras P et al (2018) Verse: versatile graph embeddings from similarity measures. In: Proceedings of the 2018 world wide web conference, pp 539–548

  47. Tu K, Cui P, Wang X et al (2018) Deep recursive network embedding with regular equivalence. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp 2357–2366

  48. Wang Y, Wang L, Li Y et al (2013) A theoretical analysis of NDCG ranking measures. In: Proceedings of the 26th annual conference on learning theory (COLT 2013), vol 8, p 6

  49. Wasserman S, Faust K (1994) Social network analysis: methods and applications, vol 8. Cambridge University Press, Cambridge

    Book  MATH  Google Scholar 

  50. Welser HT, Cosley D, Kossinets G, et al (2011) Finding social roles in wikipedia. In: Proceedings of the 2011 ACM iConference, pp 122–129

  51. West DB et al (2001) Introduction to graph theory, vol 2. Prentice-Hall, Upper Saddle River

    Google Scholar 

  52. Wuchty S, Jones BF, Uzzi B (2007) The increasing dominance of teams in production of knowledge. Science 316(5827):1036–1039

    Article  Google Scholar 

  53. Yang AY, Genesh A, Zhou Z et al (2010) A review of fast l (1)-minimization algorithms for robust face recognition. Technical report, Department of Electrical Engineering and Computer Sciences at UC Berkeley

  54. Yuan GX, Chang KW, Hsieh CJ et al (2010) A comparison of optimization methods and software for large-scale l1-regularized linear classification. J Mach Learn Res 11(11):3183–3234

    MathSciNet  MATH  Google Scholar 

  55. Yu S, Christakopoulou E, Gupta A (2016) Identifying decision makers from professional social networks. In: Proceedings of the 22nd ACM international conference on knowledge discovery and data mining, pp 333–342

  56. Zhao J, Xie X, Xu X, Sun S (2017) Multi-view learning overview: recent progress and new challenges. Inf Fusion 38:43–54

    Article  Google Scholar 

  57. Zhao Y, Wang G, Yu PS et al (2013) Inferring social roles and statuses in social networks. In: Proceedings of the 19th ACM international conference on Knowledge discovery and data mining, pp 695–703

Download references

Acknowledgements

The work was supported by partially supported by Natural Science Foundation of China (Grant Nos. 71704096 and 61602278), the Taishan Scholars Program of Shandong Province of China (Grant No. TS20190936), Shandong University of Science and Technology Research Fund (Grant No. 2015TDJH102) and the Science and Technology Support Plan of Youth Innovation Team of Shandong Higher School (Grant No. 2019KJN024).

Author information

Authors and Affiliations

  1. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China

    Weijian Ni, Haoyu Guo, Tong Liu & Qingtian Zeng

Authors
  1. Weijian Ni
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haoyu Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qingtian Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tong Liu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ni, W., Guo, H., Liu, T. et al. Automatic role identification for research teams with ranking multi-view machines. Knowl Inf Syst 62, 4681–4716 (2020). https://doi.org/10.1007/s10115-020-01504-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-020-01504-w

Keywords

Search

Navigation