Scholarlink

This short paper presents a dataset that contains a network graph, which captures relationships between football (soccer) players depending on whether they have been teammates. Most specifically, the dataset captures the co-appearance of players as members of the same squad in the UK Premier League over 30 seasons, spanning from the 1992–93 season to the 2021–22 season (inclusive). Such a dataset can be considered as a collaboration network graph and can facilitate a wide range of research applications. In sports analytics, it can be used to study player movement between teams, the impact of such movement on the network, and the career trajectories of players. In network science, it can provide a real-world example of network structures, allowing researchers to explore theories related to network evolution, formation, stability, and resilience. Additionally, this dataset can aid the development of machine learning models aimed at predicting team performance, player synergy, and the potential success of future team compositions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Novel Network Dataset Based on Football Players’ Co-appearances

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Ahmad Zareie,
  • Rizos Sakellariou

摘要

This short paper presents a dataset that contains a network graph, which captures relationships between football (soccer) players depending on whether they have been teammates. Most specifically, the dataset captures the co-appearance of players as members of the same squad in the UK Premier League over 30 seasons, spanning from the 1992–93 season to the 2021–22 season (inclusive). Such a dataset can be considered as a collaboration network graph and can facilitate a wide range of research applications. In sports analytics, it can be used to study player movement between teams, the impact of such movement on the network, and the career trajectories of players. In network science, it can provide a real-world example of network structures, allowing researchers to explore theories related to network evolution, formation, stability, and resilience. Additionally, this dataset can aid the development of machine learning models aimed at predicting team performance, player synergy, and the potential success of future team compositions.