A Link Analysis Based Approach to Predict Character Death in Game of Thrones

  • Swati AgarwalEmail author
  • Rahul Thakur
  • Sudeepta Mishra
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 309)


Mysterious and uncertain deaths in the “Game of Thrones” novel-series have been stupefying to the vast pool of readers and hence interested researchers to come up with various models to predict the deaths. In this paper, we propose a Death-Prone Score model to predict if the candidate character is going to die or stay alive in the upcoming book in the series. We address the challenge of high-dimensional data and train our model on the most significant attributes by computing feature importance in the vector space. Further, we address the challenge of multiple interactions between characters and create a social network representing the weighted similarity between each character pair in the book. The proposed model takes similarity and proximity in a social network into account and generates a death-prone score for each character. To evaluate our model, we divide the characters data into training (characters died before year 300) and testing (characters died in the year 300 and characters alive till year 300). Our results show that the proposed Death-Prone Score model achieves an f-score of 86.2%.


Character similarity Death prediction Feature importance Game of Thrones Social network analysis Weighted vector space model 


  1. 1.
    Athey, S., Tibshirani, J., Wager, S., et al.: Generalized random forests. Ann. Stat. 47(2), 1148–1178 (2019)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Beveridge, A., Shan, J.: Network of thrones. Math Horiz. 23(4), 18–22 (2016)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Boldi, P., Santini, M., Vigna, S.: PageRank as a function of the damping factor. In: Proceedings of the 14th International Conference on World Wide Web, pp. 557–566. ACM, New York (2005)Google Scholar
  4. 4.
    Bonato, A., D’Angelo, D.R., Elenberg, E.R., Gleich, D.F., Hou, Y.: Mining and modeling character networks. In: Bonato, A., Graham, F.C., Prałat, P. (eds.) WAW 2016. LNCS, vol. 10088, pp. 100–114. Springer, Cham (2016). Scholar
  5. 5.
    Chakrabarti, S.: Dynamic personalized pagerank in entity-relation graphs. In: Proceedings of the 16th International Conference on WWW, pp. 571–580 (2007)Google Scholar
  6. 6.
    Farine, D.R.: When to choose dynamic vs. static social network analysis. J. Anim. Ecol. 87(1), 128–138 (2018) CrossRefGoogle Scholar
  7. 7.
    Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3–42 (2006)CrossRefGoogle Scholar
  8. 8.
    Haghani, S., Keyvanpour, M.R.: A systemic analysis of link prediction in social network. Artif. Intell. Rev. 52(3), 1961–1995 (2019)CrossRefGoogle Scholar
  9. 9.
    Ibnoulouafi, A., Haziti, M.E., Cherifi, H.: M-centrality: identifying key nodes based on global position and local degree variation. J. Stat. Mech.: Theory Exp. 2018(7), 073407 (2018). Scholar
  10. 10.
    Janosov, M.: Network science predicts who dies next in game of thrones. Department of Network and Data Science Group at Central European University (2017).
  11. 11.
    Jia, R., Liang, P.: A game of thrones: power structure and the stability of regimes. In: Wärneryd, K. (ed.) The Economics of Conflict: Theory and Empirical Evidence. CESifo Seminar Series, pp. 79–104. MIT Press, Cambridge (2014)CrossRefGoogle Scholar
  12. 12.
    Lakiotaki, K., Delias, P., Sakkalis, V., Matsatsinis, N.F.: User profiling based on multi-criteria analysis: the role of utility functions. Oper. Res. Int. J. 9(1), 3–16 (2009)CrossRefGoogle Scholar
  13. 13.
    Liben-Nowell, D., Kleinberg, J.: The link-prediction problem for social networks. J. Am. Soc. Inf. Sci. Technol. 58(7), 1019–1031 (2007) CrossRefGoogle Scholar
  14. 14.
    Maurella, C., et al.: Social network analysis and risk assessment: an example of introducing an exotic animal disease in Italy. Microb. Risk Anal. 13 (2019). ISSN: 2352-3522
  15. 15.
    Moradabadi, B., Meybodi, M.R.: Link prediction in weighted social networks using learning automata. Eng. Appl. Artif. Intell. 70, 16–24 (2018)CrossRefGoogle Scholar
  16. 16.
    Pierce, E., Kahle, B., Downey, A.: Bayesian survival analysis for “game of thrones”. A blog by Allen Downey (2015).
  17. 17.
    Sah, P., Mann, J., Bansal, S.: Disease implications of animal social network structure: a synthesis across social systems. J. Anim. Ecol. 87(3), 546–558 (2018)CrossRefGoogle Scholar
  18. 18.
    Schubart, R., Gjelsvik, A.: Women of Ice and Fire: Gender, Game of Thrones and Multiple Media Engagements. Bloomsbury, New York (2016)Google Scholar
  19. 19.
    Shurkin, J.: Using social networks to analyze the classics. Inside Science (2012).
  20. 20.
    Tracy, P.: Using big data to accurately predict death in the ‘game of thrones’ series. Intelligence on all things wireless, RCR Wireless News (2016).
  21. 21.
    Tschiatschek, S., Singla, A., Gomez Rodriguez, M., Merchant, A., Krause, A.: Fake news detection in social networks via crowd signals. In: Companion Proceedings of the The Web Conference 2018, pp. 517–524. International World Wide Web Conferences Steering Committee (2018)Google Scholar
  22. 22.
    Zhang, Y., Mu, L., Shen, G., Yu, Y., Han, C.: Fault diagnosis strategy of CNC machine tools based on cascading failure. J. Intell. Manuf. 30(5), 2193–2202 (2019)CrossRefGoogle Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020

Authors and Affiliations

  1. 1.BITS Pilani, Goa CampusGoaIndia
  2. 2.IIT RoorkeeRoorkeeIndia
  3. 3.BITS Pilani, Hyderabad CampusHyderabadIndia

Personalised recommendations