Skip to main content

Multi-agent celebrity recommender system (MACeRS): Twitter use case


The advancement of social communities and virtual interaction of thoughts have apparently made social networking one of the fastest-growing concepts. The interaction carries meanings beyond friendship and is applied to larger areas, such as communities and networks for business, trade, cinema, and broadcasting. In a social network, the user wants to find her/his interests, and by doing so the community, to which he/she belongs, develops and grows. However, the lack of important and useful information, and sometimes its inaccessibility, hinders users from establishing good connections, and as a consequence, it hinders expanding the community. The current paper presents a method of celebrity-based friend recommendation system based on the preferences and tendencies of the user and his/her friends. The proposed method introduces a novel way of extracting and modeling the recommendation process as a game theory problem with two main agents (Celebrity and Non-Celebrity) for selecting the members with more than 10000 followers, as celebrities, to be recommended. We have used the real data from Twitter social network celebrity members to test and analyze our proposed system from two aspects, i.e., recommender system and social network. The outcomes show that almost all the items recommended by MACeRS are celebrities (99%). Moreover, the accuracy of MACeRS is significantly better than other baseline methods.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6




  • Alvari H, Hashemi S, Hamzeh A (2011) Detecting overlapping communities in social networks by game theory and structural equivalence concept. Springer, Berlin, pp 620–630

    Google Scholar 

  • Bian L, Holtzman H (2011) Online friend recommendation through personality matching and collaborative filtering. In: Proceedings of the UBICOMM, pp 230–235

  • Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3(Jan):993–1022

    MATH  Google Scholar 

  • Bliss CA, Frank MR, Danforth CM, Dodds PS (2014) An evolutionary algorithm approach to link prediction in dynamic social networks. J Comput Sci 5(5):750–764

    MathSciNet  Article  Google Scholar 

  • Bu Z, Wang Y, Li H-J, Jiang J, Wu Z, Cao J (2019) Link prediction in temporal networks: integrating survival analysis and game theory. Inf Sci 498:41–61

    MathSciNet  Article  Google Scholar 

  • Burke R (2007) Hybrid web recommender systems. The adaptive web. Springer, pp 377–408

  • Burke R (2002) Hybrid recommender systems: survey and experiments. User Model User-Adapted Interact 12(4):331–370

    Article  Google Scholar 

  • Carvalho LAMC, Macedo HT (2013) Users’ satisfaction in recommendation systems for groups: an approach based on noncooperative games, pp 951–958

  • Chang C-J, Tsai T-L, Chen Y-H(2009) Utility and game-theory based network selection scheme in heterogeneous wireless networks. IEEE, pp 1–5

  • Cheng S, Zhang B, Zou G, Huang M, Zhang Z (2019) Friend recommendation in social networks based on multi-source information fusion. Int J Mach Learn Cybern 10(5):1003–1024

    Article  Google Scholar 

  • Chu C-H, Wu W-C, Wang C-C, Chen T-S, Chen J-J (2013). Friend recommendation for location-based mobile social networks. IEEE, pp 365–370

  • Debnath S, Ganguly N, Mitra P (2008) Feature weighting in content based recommendation system using social network analysis. pp 1041–1042

  • Del Olmo FH, Gaudioso E (2008) Evaluation of recommender systems: a new approach. Expert Syst Appl 35(3):790–804

    Article  Google Scholar 

  • Ding X, Jin X, Li Y, Li L (2013) Celebrity recommendation with collaborative social topic regression

  • Ge M, Delgado-Battenfeld C, Jannach D (2010) Beyond accuracy: evaluating recommender systems by coverage and serendipity. ACM, pp 257–260

  • Halkidi M, Koutsopoulos I (2011) A game theoretic framework for data privacy preservation in recommender systems. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, pp 629–644

  • Herlocker JL, Konstan JA, Riedl J (2000) Explaining collaborative filtering recommendations. pp 241–250

  • Jain P, Guru SK (2016) Friend recommendation using FLDA topic assignment model in microblogging system. Int J Innovat Res Comput Commun Eng 4(5)

  • Kwak H, Lee C, Park H, Moon S (2010) What is twitter, a social network or a news media? pp 591–600

  • Li J, Zhang L, Meng F, Li F (2014) Recommendation algorithm based on link prediction and domain knowledge in retail transactions. Procedia Comput Sci 31:875–881

    Article  Google Scholar 

  • Liben-Nowell D, Kleinberg J (2007) The link-prediction problem for social networks. J Am Soc Inf Sci Technol 58(7):1019–1031

    Article  Google Scholar 

  • Lim M, Abdullah A, Jhanjhi NZ, Supramaniam M (2019) Hidden link prediction in criminal networks using the deep reinforcement learning technique. Computers 8(1):8

    Article  Google Scholar 

  • Liu F, Li M (2019) A game theory-based network rumor spreading model: based on game experiments. Int J Mach Learn Cybern 10(6):1449–1457

    Article  Google Scholar 

  • Manshaei MH, Zhu Q, Alpcan T, Bacşar T, Hubaux J-P (2013) Game theory meets network security and privacy. ACM Comput Surv (CSUR) 45(3):1–39

    Article  Google Scholar 

  • Moradabadi B, Meybodi MR (2018) Link prediction in weighted social networks using learning automata. Eng Appl Artif Intell 70:16–24

    Article  Google Scholar 

  • Myerson RB (2013) Game theory. Harvard University Press, Cambridge

    Book  Google Scholar 

  • Papadimitriou A, Symeonidis P, Manolopoulos Y (2012) Fast and accurate link prediction in social networking systems. J Syst Softw 85(9):2119–2132

    Article  Google Scholar 

  • Parvathy, VS, and TK Ratheesh (2017) Friend recommendation system for online social networks: a survey, vol 2. IEEE, pp 359–365

  • Pazzani MJ, Billsus D (2007) Content-based recommendation systems. The adaptive web. Springer, pp 325–341

  • Popescul A, Ungar LH, Pennock DM, Lawrence S (2013) Probabilistic models for unified collaborative and content-based recommendation in sparse-data environments. arXiv preprint arXiv:1301.2303

  • Roozbahani Z, Rezaeenour J, Emamgholizadeh H, Bidgoly AJ (2020) A systematic survey on collaborator finding systems in scientific social networks. Knowl Inf Syst J 63(6)

  • Roughgarden T (2010) Algorithmic game theory. Commun ACM 53(7):78–86

    Article  Google Scholar 

  • Saga R, Okamoto K, Tsuji H, Matsumoto K (2013) Evaluating recommender system using multiagent-based simulator. In: Recent Progress in Data Engineering and Internet Technology. Springer, pp 155–162

  • Sarwar B, Karypis G, Konstan J, Riedl J (2001) Item-based collaborative filtering recommendation algorithms. pp 285–295

  • Schafer JB, Frankowski D, Herlocker J, Sen S (2007) Collaborative filtering recommender systems. The adaptive web. Springer, pp 291–324

  • Schröder G , Thiele M, Lehner W (2011) Setting goals and choosing metrics for recommender system evaluations, vol 23. Chicago, USA, p page 53

  • Tajbakhsh MS, Aghababa MP, Solouk V, Akbari-Moghanjoughi A (2013) Friend recommendation based on the luscher color theory: Twitter use case. IEEE, pp 218–221

  • Tang F, Zhang B, Zheng J, Gu Y (2013) Friend recommendation based on the similarity of micro-blog user model. IEEE, pp 2200–2204

  • Tarkowski M, Michalak T, Wooldridge M (2019) A game-theoretic algorithm for link prediction. arXiv preprint arXiv:1912.12846

  • Trestian R, Ormond O, Muntean G-M (2011) Reputation-based network selection mechanism using game theory. Phys Commun 4(3):156–171

    Article  Google Scholar 

  • Trestian R, Ormond O, Muntean G-M (2012) Game theory-based network selection: Solutions and challenges. IEEE Commun Surv Tutor 14(4):1212–1231

    Article  Google Scholar 

  • Tsvetovat M, Kouznetsov A (2011) Social Network Analysis for Startups: Finding connections on the social web. O’Reilly Media Inc

  • Tuan TM, Chuan PM, Ali M, Ngan TT, Mittal M et al (2019) Fuzzy and neutrosophic modeling for link prediction in social networks. Evolv Syst 10(4):629–634

    Article  Google Scholar 

  • Verma J, Gupta S, Mukherjee D, Chakraborty T (2019) Heterogeneous edge embedding for friend recommendation. Springer, Berlin, pp 172–179

    Google Scholar 

  • Xu Y, Zhou D, Ma J (2019) Scholar-friend recommendation in online academic communities: an approach based on heterogeneous network. Decis Support Syst 119:1–13

    Article  Google Scholar 

  • Zaier Z, Godin R, Faucher L(2008) Evaluating recommender systems. IEEE, pp 211–217

  • Zhang M, Yixin C (2018) Link prediction based on graph neural networks. In: Advances in Neural Information Processing Systems, pp 5165–5175

  • Zhao T, Zhao H, King I (2015) Exploiting game theoretic analysis for link recommendation in social networks, pp 851–860

  • Zheng N, Song S, Bao H (2015) A temporal-topic model for friend recommendations in Chinese microblogging systems. IEEE Trans Syst Man Cybern Syst 45(9):1245–1253

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Mir Saman Tajbakhsh.

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

Verify currency and authenticity via CrossMark

Cite this article

Tajbakhsh, M.S., Emamgholizadeh, H., Solouk, V. et al. Multi-agent celebrity recommender system (MACeRS): Twitter use case. Soc. Netw. Anal. Min. 12, 11 (2022).

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI:


  • Recommender System
  • Multi-Agent System
  • Celebrity Recommendation
  • Social Network
  • Friend Recommender System
  • Twitter