Measuring Soccer Players’ Influence on Flow and Path Complexity of Team Passes Based on Metrics of Complex Network Analysis

Document Type : Persian Original Article

Authors

1 Software Engineering Group, Department of Computer Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran

2 Department of Computer Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran

Abstract

Soccer coaches and analyzers require deep and precise analysis of matches. In this paper, we focus on the analysis of passes in soccer matches using complex networks and social networks theories and propose novel metrics with deeper analysis than traditional metrics such as the numbers of passes and accuracy. To this end, based on accurate recorded data of passes in a match, two different networks are extracted where the first network is comprised of all passes of a team in a match to overlay analyze the team behavior for ball circulation. The second network is comprised of offensive passes to analyze offensive attacks of a team in a match. Based on the structure of these networks, we propose three quantitative metrics to measure three important parameters including availability of players, impact of one player on the flow of a team, and the complexity of the passing path between players. Using these three important parameters, teams can investigate their strengths and weaknesses in passing flow. To evaluate the proposed approach, we applied it to the actual data of a team in several consecutive matches. The results reveal that the proposed approach can accurately analyze the impact of players on the success of team during a match.

Keywords

References

 [1] FIFA. "2018 FIFA World Cup Russia™ Global broadcast and
audience summary,"
https://resources.fifa.com/image/upload/njqsntrvdvqv8ho1dag5.pdf
.
[2] R. Ievoli, L. Palazzo, and G. Ragozini, “On the use of passing
network indicators to predict football outcomes,” Knowledge-Based
Systems, vol. 222, pp. 106997, 2021/06/21/, 2021.
[3] K. Bray, How to Score: Science and the Beautiful Game: Granta
Books, 2008.
[4] J. López Peña, and H. Touchette, “A network theory analysis of
football strategies,” arXiv, pp. arXiv: 1206.6904, 2012.
[5] A. Joseph, N. Fenton, and M. Neil, “Predicting football results using
Bayesian nets and other machine learning techniques,” Knowl.
Based Syst., vol. 19, no. 7, pp. 544-553, 2006.
[6] R. Rein, D. Raabe, and D. Memmert, “"Which pass is better?" Novel
approaches to assess passing effectiveness in elite soccer,” Human
movement science, vol. 55, pp. 172-181, 2017.
[7] E. Arriaza-Ardiles, J. A. Martin-Gonzalez, M. D. Zuniga et al.,
“Applying graphs and complex networks to football metric
interpretation,” Human movement science, vol. 57, pp. 236-243,
2018.
[8] S. P. Borgatti, M. G. Everett, and J. C. Johnson, Analyzing social
networks: Sage, 2018.
[9] J. M. Buldu, J. Busquets, and I. Echegoyen, “Defining a historic
football team: Using Network Science to analyze Guardiola’s FC
Barcelona,” Scientific reports, vol. 9, no. 1, pp. 1-14, 2019.
[10] J. Duch, J. S. Waitzman, and L. A. N. Amaral, “Quantifying the
Performance of Individual Players in a Team Activity,” PLOS ONE,
vol. 5, no. 6, pp. e10937, 2010.
[11] H. Sarmento, F. M. Clemente, E. Gonçalves et al., “Analysis of the
offensive process of AS Monaco professional soccer team: A mixedmethod approach,” Chaos, Solitons & Fractals, vol. 133, pp.
109676, 2020/04/01/, 2020.
[12] I. G. McHale, and S. Relton, “Identifying Key Players in Soccer
Teams using Network Analysis and Pass Difficulty,” European
Journal of Operational Research, vol. 268, no. 1, pp. 339-347, 2018.
[13] Y. Wu, Z. Xia, T. Wu et al., “Characteristics and optimization of
core local network: Big data analysis of football matches,” Chaos,
Solitons & Fractals, vol. 138, pp. 110136, 2020/09/01/, 2020.
[14] R. Kooij, A. Jamakovic, F. Kesteren et al., “The Dutch Soccer Team
as a Social Network,” Connections, Vol. 29. No. 1, 2009, 2009.
[15] M. E. Newman, “The structure and function of complex networks,”
SIAM review, vol. 45, no. 2, pp. 167-256, 2003.
[16] Y. Cho, J. Yoon, and S. Lee, “Using social network analysis and
gradient boosting to develop a soccer win–lose prediction model,”
Engineering Applications of Artificial Intelligence, vol. 72, pp. 228-
240, 2018/06/01/, 2018.
[17] "Sepehr Company," 2020; https://www.sepehrco.ir/.
[18] L. C. Freeman, “Centrality in social networks conceptual
clarification,” Social Networks, vol. 1, no. 3, pp. 215-239,
1978/01/01/, 1978.
[19] U. Brandes, “On variants of shortest-path betweenness centrality and
their generic computation,” Social Networks, vol. 30, no. 2, pp. 136-
145, 2008/05/01/, 2008.
[20] D. J. MacKay, Information theory, inference and learning
algorithms: Cambridge university press, 2003.
[21] J. Saramäki, M. Kivelä, J.-P. Onnela et al., “Generalizations of the
clustering coefficient to weighted complex networks,” Physical
Review E, vol. 75, no. 2, pp. 027105, 2007.
[22] G. Fagiolo, “Clustering in complex directed networks,” Physical
Review E, vol. 76, no. 2, pp. 026107, 2007.
[23] T. Decroos, J. Van Haaren, V. Dzyuba et al., "STARSS: a spatiotemporal action rating system for soccer," in Machine Learning and
Data Mining for Sports Analytics ECML/PKDD 2017 workshop,
2017, vol. 1971: Springer, pp. 11-20. 
Journal of Soft Computing and Information Technology
Volume 10, Issue 4 - Serial Number 34
Winter
January 2022
Pages 68-87

Files

Share

How to cite

Statistics