Clustering Player Metrics from Counter-Strike: Global Offensive Esports Tournaments for Analyzing Consistency in Pistol Round Behavior

• Item type: SIG Technical Reports(1)
• 公開日: 2024-03-01
• タイトル: Clustering Player Metrics from Counter-Strike: Global Offensive Esports Tournaments for Analyzing Consistency in Pistol Round Behavior
• タイトル / 言語: en
• タイトル: Clustering Player Metrics from Counter-Strike: Global Offensive Esports Tournaments for Analyzing Consistency in Pistol Round Behavior
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: The University of Tokyo
• 著者所属: The University of Tokyo
• 著者所属: The University of Tokyo
• 著者所属: The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者名: Franziska, Zimmer; Mhd, Irvan; Ryosuke, Kobayashi; Rie, Shigetomi Yamaguchi
• 著者名(英): Franziska, Zimmer; Mhd, Irvan; Ryosuke, Kobayashi; Rie, Shigetomi Yamaguchi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This study examines player behavior in Counter-Strike: Global Offensive (CS:GO) pistol rounds through clustering analysis using the Esports Trajectories & Actions (ESTA) dataset, spanning January 2021 to May 2022. Focusing on the top 50 active players, we analyzed 10,500 pistol rounds, applying DBSCAN clustering to pre-processed player metrics. Key findings reveal four distinct clusters: early eliminated players, sharpshooters, strategists utilizing utilities, and versatile players combining high headshot rates with strategic utility use. Key features used describe utility usage, combat engagement, and objective-focused gameplay. Stability in cluster assignments suggests consistent groupings of playing behaviors across rounds, with varying consistency levels across clusters and player behavior. Future research should explore time-and place-based behaviors to further dissect playing patterns.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This study examines player behavior in Counter-Strike: Global Offensive (CS:GO) pistol rounds through clustering analysis using the Esports Trajectories & Actions (ESTA) dataset, spanning January 2021 to May 2022. Focusing on the top 50 active players, we analyzed 10,500 pistol rounds, applying DBSCAN clustering to pre-processed player metrics. Key findings reveal four distinct clusters: early eliminated players, sharpshooters, strategists utilizing utilities, and versatile players combining high headshot rates with strategic utility use. Key features used describe utility usage, combat engagement, and objective-focused gameplay. Stability in cluster assignments suggests consistent groupings of playing behaviors across rounds, with varying consistency levels across clusters and player behavior. Future research should explore time-and place-based behaviors to further dissect playing patterns.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11362144
• 書誌情報: 研究報告ゲーム情報学（GI）; 巻 2024-GI-51, 号 5, p. 1-7, 発行日 2024-03-01
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8736
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会