Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input

Large-scale match data from esports games like League of Legends are stored in complex JSON files that often exceed the input token limitations of large language models (LLMs), restricting advanced analysis and applications such as automated commentary and strategic insight generation. This paper in...

Full description

Saved in:
Bibliographic Details
Main Authors: Jooyoung Kim, Wonkyung Lee, Jungwoon Park
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/13/7190
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850118725442732032
author Jooyoung Kim
Wonkyung Lee
Jungwoon Park
author_facet Jooyoung Kim
Wonkyung Lee
Jungwoon Park
author_sort Jooyoung Kim
collection DOAJ
description Large-scale match data from esports games like League of Legends are stored in complex JSON files that often exceed the input token limitations of large language models (LLMs), restricting advanced analysis and applications such as automated commentary and strategic insight generation. This paper introduces the League of Legends Match Data Compactor (LoL-MDC), a tool designed to transform extensive match data into a concise and structured format optimized for LLM processing. By systematically summarizing structured match information—including match overviews, player and team statistics, timeline summaries, and algorithmically selected key events—the LoL-MDC significantly reduces the data size from approximately 80,000 tokens to under 2000 tokens while retaining analytical value. This method enables LLMs to generate coherent match summaries, analyze player performances, and identify key momentum shifts more effectively than processing raw JSON files. Additionally, the LoL-MDC integrates a winning probability metric to quantitatively enhance the selection of pivotal game events, ensuring relevance in esports analytics. Experimental evaluations demonstrate that the LoL-MDC improves data processing efficiency while maintaining critical insights. The proposed approach provides a structured and adaptable framework for applying LLMs to esports analytics and can be adapted to other competitive gaming environments, supporting AI-driven applications in match analysis, player performance evaluation, and strategic forecasting.
format Article
id doaj-art-6ac6e06a799c46948df5dff1c35fbec2
institution OA Journals
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-6ac6e06a799c46948df5dff1c35fbec22025-08-20T02:35:47ZengMDPI AGApplied Sciences2076-34172025-06-011513719010.3390/app15137190Structured Summarization of League of Legends Match Data Optimized for Large Language Model InputJooyoung Kim0Wonkyung Lee1Jungwoon Park2Department of Convergence Software, Myongji University, Seoul 03674, Republic of KoreaPS Analytics, Seoul 03993, Republic of KoreaDepartment of Electrical & Electronics Engineering, Yonsei University, Seoul 03829, Republic of KoreaLarge-scale match data from esports games like League of Legends are stored in complex JSON files that often exceed the input token limitations of large language models (LLMs), restricting advanced analysis and applications such as automated commentary and strategic insight generation. This paper introduces the League of Legends Match Data Compactor (LoL-MDC), a tool designed to transform extensive match data into a concise and structured format optimized for LLM processing. By systematically summarizing structured match information—including match overviews, player and team statistics, timeline summaries, and algorithmically selected key events—the LoL-MDC significantly reduces the data size from approximately 80,000 tokens to under 2000 tokens while retaining analytical value. This method enables LLMs to generate coherent match summaries, analyze player performances, and identify key momentum shifts more effectively than processing raw JSON files. Additionally, the LoL-MDC integrates a winning probability metric to quantitatively enhance the selection of pivotal game events, ensuring relevance in esports analytics. Experimental evaluations demonstrate that the LoL-MDC improves data processing efficiency while maintaining critical insights. The proposed approach provides a structured and adaptable framework for applying LLMs to esports analytics and can be adapted to other competitive gaming environments, supporting AI-driven applications in match analysis, player performance evaluation, and strategic forecasting.https://www.mdpi.com/2076-3417/15/13/7190esports analyticsLeague of LegendsJSON data processingdata compressionlarge language models
spellingShingle Jooyoung Kim
Wonkyung Lee
Jungwoon Park
Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input
Applied Sciences
esports analytics
League of Legends
JSON data processing
data compression
large language models
title Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input
title_full Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input
title_fullStr Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input
title_full_unstemmed Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input
title_short Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input
title_sort structured summarization of league of legends match data optimized for large language model input
topic esports analytics
League of Legends
JSON data processing
data compression
large language models
url https://www.mdpi.com/2076-3417/15/13/7190
work_keys_str_mv AT jooyoungkim structuredsummarizationofleagueoflegendsmatchdataoptimizedforlargelanguagemodelinput
AT wonkyunglee structuredsummarizationofleagueoflegendsmatchdataoptimizedforlargelanguagemodelinput
AT jungwoonpark structuredsummarizationofleagueoflegendsmatchdataoptimizedforlargelanguagemodelinput