Back to search

University of York

Applying machine learning to enhance esport broadcast narratives

Abstract

dc:description.abstract

Esports has emerged as one of the fastest-growing entertainment phenomena, blending the excitement of traditional sports with the immersive, digital environment of online gaming. Fuelled by the popularity of games broadcast, esports commands a massive audience that demands increasingly engaging and immersive experiences. This drives tournament organisers and broadcasters to seek innovative ways to meet these expectations. The digital nature of esports provides a wealth of accessible data, making it an ideal domain for advancements in Artificial Intelligence (AI) and Machine Learning (ML). This motivates research in the domain as a meaningful data-driven solution to creating more engaging esport broadcasting experiences. However, leveraging ML to enhance esports broadcasts presents unique challenges. The fast-paced, complex nature of esports requires models that generate meaningful insights while integrating seamlessly with live coverage. Current research often struggles to bridge the gap between theoretical advancements and practical application, leaving many ML innovations underutilised in live esports broadcasts, which limits their real-world impact. This thesis addresses these challenges by exploring how ML can be applied to enhance esports broadcast narratives. It provides insights for designing models with greater longevity, ensuring they remain functional across multiple game patches. It also offers considerations for integrating ML models into live broadcast environments, enabling them to more easily complement ecological contexts in real-world applications. Furthermore, it emphasises the importance of seamless integration with existing broadcasting strategies, from production workflows to narrative creation. These findings are then condensed into a framework aimed at ML practitioners that provides practical guidance on how to apply them in to future work in the domain. By addressing these key areas, this thesis advances the practical and long-term impact of ML research in esports broadcasting and contributes to the continued evolution of this dynamic field.

Degree

thesis:*
Name dc:type.qualificationname
Ph.D
Level dc:type.qualificationlevel
doctoral
Grantor dc:publisher.institution
University of York
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Pedrassoli Chitayat, Alan
Advisors dc:contributor.advisor
  • Block, Florian
  • Walker, James
  • Drachen, Anders
ORCID person:identifier.orcid

Rights

Language dc:language.dcterms_iso639_2
eng

Identifiers

dc:identifier.*
Dc Identifier Grantnumber
EP/S022325/1

Chain of custody

source
Harvested from
White Rose University Consortium
Base URL
etheses.whiterose.ac.uk/cgi/oai2
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
related terms
citation

Pedrassoli Chitayat, Alan. Applying machine learning to enhance esport broadcast narratives. doctoral thesis, University of York, 2025.