Influence of Match Status on Players' Prominence and Teams' Network Properties During 2018 FIFA World Cup

Evolution of passing network in the Soccer World Cups 2010-2022

This study investigates the evolution of passing networks (PN) at both team and player levels in the FIFA World Cups (WC) from 2010 to 2022. Analyzing 256 matches (7328 player observations) using a multiple-camera tracking system across four WCs, we considered six playing positions: goalkeeper (n = 521), central defender (n = 1192), fullback (n = 1223), midfielder (n = 2039), winger (n = 1320), and central forward (n = 1033). We used 17 network metrics and considered contextual variables such as team formation, and team ranking. Linear mixed-effect models analyzed differences in team and player PN parameters by year and team strength. Results showed a shift from possession-play to direct-play from the 2010 to 2018 WCs, with possession-play returning in 2022. Specifically, high- and low-quality teams significantly decreased their density, average degree (AD), modularity, and average path length in 2018 (p < 0.05). High-quality teams showed increased density, AD, and average weighted degree in 2022 (p < 0.05). Midfielders and central forwards exhibited significantly lower centrality parameters, whereas central defenders and goalkeepers showed increased centrality parameters (p < 0.05). This study highlights the evolutionary trends of passing relationships from a network analysis perspective over twelve years, providing insights into the changing dynamics of team interactions and positional prominence in elite soccer.

The seven phases of match status differentiate the running performance of soccer players in UEFA Champions League

The purpose of this research was to investigate the running performance of professional soccer players in relation to seven phases which resulted in the changing or maintaining the match status in the UEFA Champion League games during season 2020/2021. Moreover, we aimed to define which match status phases occur at the earliest stage of regular game time. This study involved professional soccer players from 24 teams participating in the group stage of UEFA Champions League in season 2020/21. The match status was divided into seven phases that result in changing or maintaining the match outcome: DW (Drawing to Winning); LD (Losing to Drawing); WW (Winning to Winning); DD (Drawing to Drawing); LL (Losing to Losing); DL (Drawing to Losing); WD (Winning to Drawing). Such running performance variables as: total distance covered (TDC) and distance covered in high-intensity running (HIR) were analyzed. Players participating in the UEFA Champions League matches cover the longest TDC in DW, DL and DD phases. TDC in these stages was between 111 and 123 m min^-1. The highest HIR was recorded during phases: DW, DL and LL (range between 9.91 and 10.82 m min^-1). In contrast, the lowest total distance and distance in HIR is covered during WD phase (only 105.57 ± 1.89 m min^-1 and 7.34 m min^-1 respectively). On average, phases resulting in the change of the match status occur during the first half, while all phases maintaining the result in the second half. Coaching staffs should consider registering and analysing the physical match performance in relation to described seven match status phases. Such information allows to prepare team-specific training drills, that players should perform more often in order to change or maintain the status of the game.

Identifying Soccer Teams' Styles of Play: A Scoping and Critical Review

Identifying and measuring soccer playing styles is a very important step toward a more effective performance analysis. Exploring the different game styles that a team can adopt to enable a great performance remains under-researched. To address this challenge and identify new directions in future research in the area, this paper conducted a critical review of 40 research articles that met specific criteria. Following the 22-item Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines, this scoping review searched for literature on Google Scholar and Pub Med database. The descriptive and thematic analysis found that the objectives of the identified papers can be classified into three main categories (recognition and effectiveness of playing styles and contextual variables that affect them). Critically reviewing the studies, the paper concluded that: (i) factor analysis seems to be the best technique among inductive statistics; (ii) artificial intelligence (AI) opens new horizons in performance analysis, and (iii) there is a need for further research on the effectiveness of different playing styles, as well as on the impact of contextual variables on them.

Combined effect of game position and body size on network-based centrality measures performed by young soccer players in small-sided games

This study verified the effects of body size and game position on interactions performed by young soccer players in small-sided games (SSG). The sample consisted of 81 Brazilian soccer players (14.4 ± 1.1 years of age). Height, body mass, and trunk-cephalic height were measured. SSG was applied in the GK + 3v3 + GK format, and Social Network Analyses were carried out through filming the games to obtain the following prominence indicators: degree centrality, closeness centrality, degree prestige, and proximity prestige, in addition to network intensity and number of goals scored. Factorial ANCOVA (bone age as covariate) was used to test the effects of game position, body size, and respective interaction on centrality measurements (p < 0.05). Similarity between game positions in body size indicators (p > 0.05) was observed. The game position affected degree centrality (p = 0.01, η² = 0.16), closeness centrality (p  = 0.01, η² = 0.11), and network intensity (p = 0.02, η² = 0.09), in which midfielders presented the highest network prominence values when compared to defenders and forwards. In conclusion, midfielders are players with high interaction patterns in the main offensive plays, which behavior is independent of body size.

Graph representations for the analysis of multi-agent spatiotemporal sports data

Analyzing tactical patterns in invasion games using multi-agent spatiotemporal data is a challenging task at the intersection of computer and sports science. A fundamental yet understudied problem in this area is finding an optimal data representation for processing athlete trajectories using machine learning algorithms. In the present work, we address this gap by discussing common representations in use and propose Tactical Graphs, an alternative graph-based format capable of producing integrative, contextualized models for machine learning applications. We provide an in-depth, domain-specific motivation of the proposed data representation scheme and show how this approach exploits inherent data traits. We propose Tactical Graph Networks (TGNets), a light-weight, hybrid machine learning architecture sensitive to player interactions. Our method is evaluated with an extensive ablation study and the first comprehensive state of the art comparison between standard feature, state vector, and image-based methods on the same dataset. Experiments were conducted using real-world football data containing short sequences of defensive play labelled according to the outcome of ball winning attempts. The results indicate that TGNets are on par with state-of-the-art deep learning models while exhibiting only a fraction of their complexity. We further demonstrate that selecting the right data representation is crucial as it has a significant influence on model performance. The theoretical findings and the proposed method provide insights and a strong methodological alternative for all classification, prediction or pattern recognition applications in the areas of collective movement analysis, automated match analysis, and performance analysis.

Guardiola, Klopp, and Pochettino: The Purveyors of What? The Use of Passing Network Analysis to Identify and Compare Coaching Styles in Professional Football

We applied social networks analysis to objectively discriminate and describe interpersonal interaction dynamics of players across different top-coaching styles. The aim was to compare metrics in the passing networks of Jürgen Klopp, Pep Guardiola, and Mauricio Pochettino across the UEFA Champions League seasons from 2017 to 2020. Data on completed passes from 92 games were gathered and average passing networks metrics were computed. We were not only able to find the foundations on which these elite coaches build the passing dynamics in their respective teams, but also to determine important differences that represent their particular coaching signatures. The local cluster coefficient was the only metric not significantly different between coaches. Still, we found higher average shortest-path length for Guardiola's network (mean ± std = 3.00 ± 0.45 a.u.) compared to Klopp's (2.80 ± 0.52 a.u., p = 0.04) and Pochettino's (2.70 ± 0.39 a.u., p = 0.01). Density was higher for Guardiola's (64.16 ± 20.27 a.u.) than for Pochettino's team (51.42 ± 17.28 a.u., p = 0.008). The largest eigenvalue for Guardiola's team (65.95 ± 16.79 a.u.) was higher than for Klopp's (47.06 ± 17.25 a.u., p < 0.001) and Pochettino's (42,62 ± 12.01 a.u., p < 0.001). Centrality dispersion was also higher for Guardiola (0.14 ± 0.02 a.u.) when compared to Klopp (0.12 ± 0.03 a.u., p = 0.008). The local cluster coefficient seems to build the foundation for passing work, however, cohesion characteristics among players in the three teams of the top coaches seems to characterize their own footprint regarding passing dynamics. Guardiola stands out by the high number of passes and the enhanced connection of the most important players in the network. Klopp and Pochettino showed important similarities, which are associated to preferences toward more flexibility of interpersonal linkages synergies.

Defending in 4-4-2 or 5-3-2 formation? small differences in footballers' collective tactical behaviours

This study explored footballers' tactical behaviours, based on their position data, as an effect of two defending formations, 4-4-2 and 5-3-2, using an experimental approach. Sixty-nine youth footballers participated in this 11-versus-11 study, performing 72 trials of attack-versus-defence. Players' position data were tracked using a local positioning system, and processed to calculate measures of collective movement. This was supplemented by the analysis of passing networks. The results showed small differences between the two conditions. Compared to a 4-4-2 formation, defending in 5-3-2 reduced dispersion (-0.69 m,p=0.012), midfield-forward distance (-0.81 m, p=0.047), and defence-forward distance (-1.29 m, p=0.038); the consequent effects on attacking teams included reduced team widths (-1.78 m, p=0.034), reduced necessity for back-passes to the goalkeeper, and less connectivity in the passing network. The effects of the two defending formations seem to have the greatest impact on fullbacks of the attacking teams, since they were main contributors of the reduced team widths, received more passes, and had higher betweenness centrality in the right-back position during 5-3-2 defending. In summary, the present study potentially demonstrates how the underlying mechanisms in players' collective movements and passing behaviours show that the 5-3-2 is more conservatively defensive than the 4-4-2.

Coexistence of Distinct Performance Models in High-Level Women's Volleyball

In performance analysis, and most notably in match analysis, generalizing game patterns in a sport or competition may result in formulating generic models and neglecting relevant variability in benefit of average or central values. Here, we aimed to understand how different game models can coexist at the same competitive level using social network analysis with degree centrality to obtain systemic mappings for six volleyball matches, one for each of the six national teams playing in the 2014 World Grand Prix Finals, guaranteeing a homogeneous game level and balanced matches. Although the sample was not recent, this was not relevant for our purposes, since we aimed to merely expose a proof of concept. A total of 56 sets and 7,176 ball possessions were analysed through Gephi Software, considering game actions as nodes and the interaction between them as edges. Results supported the coexistence of different performance models at the highest levels of practice, with each of the six teams presenting a very distinct game model. For example, important differences in eigenvector centrality in attack zones (ranging from 0 to 34) and tempos (20 to 38) were found between the six teams, as well as in defensive lines (20 to 39) and block opposition (22 to 37). This further suggests that there may be multiple pathways towards expert performance within any given sport, inviting a re-conceptualization of monolithic talent identification, detection and selection models. Future studies could benefit from standardizing the metrics in function of the number of ball possessions.

Passing Networks and Tactical Action in Football: A Systematic Review

The aim of this study is to examine the most significant literature on network analyses and factors associated with tactical action in football. A systematic review was conducted on Web of Science, taking into account the PRISMA guidelines using the keyword “network”, associated with “football” or “soccer”. The search yielded 162 articles, 24 of which met the inclusion criteria. Significant results: (a) 50% of the studies ratify the importance of network structures, quantifying and comparing properties to determine the applicability of the results instead of analyzing them separately; (b) 12.5% analyze the process of offensive sequences and communication between teammates by means of goals scored; (c) the studies mainly identify a balance in the processes of passing networks; (d) the variables allowed for the interpretation of analyses of grouping metrics, centralization, density and heterogeneity in connections between players of the same team. Finally, a systematic analysis provides a functional understanding of knowledge that will help improve the performance of players and choose the most appropriate response within the circumstances of the game.

Effects of match period and playing position on the individual and collective dynamics in professional soccer: a case study

Abstract This study aimed to compare the width, the length, the length per width ratio, and the stretch index between the first and the second halves in official soccer matches, and to compare the spatial exploration index between players from different positions. Seventeen professional soccer players from a Brazilian club participated in the study and were monitored during six official matches by a GPS device. Collective positional data were compared between the two halves using a paired t-test, while the spatial exploration index was compared between the playing positions and within the halves by a mixed two-way ANOVA. The results revealed no differences between the two halves for the collective variables. The highest values of spatial exploration index were reported for central midfielders and wing forwards. We conclude that the tactical behavior of professional soccer players is position-dependent, and midfielders are the most exploratory players on the pitch.

Play-by-Play Network Analysis in Football

This study identifies dominant and intermediary players in football by applying a play-by-play social network analysis (SNA) on 70 professional matches from the 1. and 2. German Bundesliga during the 2017/2018 season. SNA provides a quantification of the complex interaction patterns between players in team sports. So far, the individual contributions and roles of players in football have only been studied at match-level considering the overall passing of a team. In order to consider the real structure of football, a play-by-play network analysis is needed that reflects actual interplay. Moreover, a distinction between plays of certain characteristics is important to qualify different interaction phases. As it is often impossible to calculate well known network metrics such as betweenness on play-level, new adequate metrics are required. Therefore, flow betweenness is introduced as a new playmaker indicator on play-level and computed alongside flow centrality. The data on passing and the position of players was provided by the Deutsche Fußball Liga (DFL) and gathered through a semi-automatic multiple-camera tracking system. Central defenders are identified as dominant and intermediary players, however, mostly in unsuccessful plays. Offensive midfielders are most involved and defensive midfielders are the main intermediary players in successful plays. Forward are frequently involved in successful plays but show negligible playmaker status. Play-by-play network analysis facilitates a better understanding of the role of players in football interaction.

The Validity and Reliability of Live Football Match Statistics From Champdas Master Match Analysis System

The aim of the present study was to investigate the validity of match variables and the reliability of Champdas Master System used by trained operators in live association football match. Twenty professional football coaches voluntarily participated in the validation of match variables used in the System. Four well-trained operators divided into two groups that independently analyzed a match of Spanish La Liga. The Aiken’s V averaged at 0.84 ± 0.03 and 0.85 ± 0.03 for the validation of indicators. The high Kappa values (Operator 1: 0.92, 0.90; Operator 2: 0.91, 0.88), high intra-class correlation coefficients (varied from 0.93 to 1.00), and low typical errors (varied from 0.01 to 0.34) between the first and second data collection represented a high level of intra-operator reliability. The Kappa values for the inter-operator reliability of were 0.97 and 0.89. The intra-class correlation coefficients and typical errors ranged from 0.90 to 1.00 and ranged from 0.01 to 0.24 for two independent operators within two data collections. The results suggest that the Champdas Master system can be used validly and reliably to gather live football match statistics by well-trained operators. Therefore, the data obtained by the company can be used by coaches, managers, researchers and performance analysts as valid match statistics from players and teams during their professional tasks and investigations.