Document Type
Article
Source Publication Title
2023 8th International Conference on Information Systems Engineering
DOI
https://dl.acm.org/doi/10.1145/3641032.3641066
Abstract
Effective teamwork is crucial for organizational success, yet few studies have quantified the influence and combination embedded within the collaboration process. This study aims to extend the representation learning model to quantify the effectiveness of teamwork collaborations and identify the most influential group in every individual’s combination. We leverage the unique NBA 2K dataset, containing individual skillset attributes and labeled player levels, to mark the hierarchy value based on skill sets. By transforming the hierarchical structure of teams into vector representations, we provide a comprehensive understanding of the influence and combination within teamwork collaborations. Our findings contribute to the literature on teamwork dynamics, offering valuable insights for organizations seeking to optimize group-level influence and performance. Furthermore, the methodology presented in this study has the potential for generalization to other organizational contexts, enabling a broader application of representation learning models in understanding teamwork effectiveness.
Publication Date
6-11-2024
Language
English
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Zheng, Tianzi, "Quantifying Team Dynamics and Performance: A Hierarchical Representation Learning Approach using the NBA 2K Dataset" (2024). Association of Computing Machinery Open Access Agreement Publications-Archive. 95.
https://mavmatrix.uta.edu/utalibraries_acmoapubs/95