Structured Summarization of League of Legends Match Data Optimized for Large Language Model Input
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Web Data Mining and Analysis · Topic Modeling · Video Analysis and Summarization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Convergence Software, Myongji University, Seoul 03674, Republic of Korea
PS Analytics, Seoul 03993, Republic of Korea
Department of Electrical & Electronics Engineering, Yonsei University, Seoul 03829, Republic of Korea
Funding
2024 Research Fund of Myongji University
References (30)
Show source-provided references
1. Riot Games (2025, June 23). League of Legends. Available online: https://www.leagueoflegends.com/.
2. Factors affecting eSports audience satisfaction-The case of League of Legends10.7583/JKGS.2014.14.3.35 ↗
3. Gaming the gift: The affective economy of League of Legends ‘fair’free-to-play model10.1177/1469540521993932 ↗
4. A motivational model of video game engagement10.1037/a0019440 ↗
5. Riot Games (2025, June 23). Riot Games API. Available online: https://developer.riotgames.com/.
6. Gallotta, R., Todd, G., Zammit, M., Earle, S., Liapis, A., Togelius, J., and Yannakakis, G.N. (2024). Large language models and games: A survey and roadmap. arXiv.10.1109/TG.2024.3461510 ↗
7. OpenAI (2025, June 23). OpenAI Platform. Available online: https://platform.openai.com/.
8. Zhong, Z., Liu, H., Cui, X., Zhang, X., and Qin, Z. (2024). Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation. arXiv.
9. Yepes, A.J., You, Y., Milczek, J., Laverde, S., and Li, R. (2024). Financial report chunking for effective retrieval augmented generation. arXiv.
10. Win prediction in multiplayer esports: Live professional match prediction10.1109/TG.2019.2948469 ↗
11. Machine learning methods for predicting league of legends game outcome
12. Performance analysis in esports: Modelling performance at the 2018 League of Legends World Championship10.1177/1747954120932853 ↗
13. Choi, E., Kim, J., and Lee, W. (2023, January 1–3). Rethinking Evaluation Metric for Probability Estimation Models Using Esports Data. Proceedings of the 2023 IEEE 22nd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), Exeter, UK.10.1109/TrustCom60117.2023.00374 ↗
14. Sensors and game synchronization for data analysis in esports10.1109/INDIN41052.2019.8972249 ↗
15. Block, F., Hodge, V., Hobson, S., Sephton, N., Devlin, S., Ursu, M.F., Drachen, A., and Cowling, P.I. (2018, January 26–28). Narrative bytes: Data-driven content production in esports. Proceedings of the 2018 ACM International Conference on Interactive Experiences for TV and Online Video, Seoul, Republic of Korea.10.1145/3210825.3210833 ↗
16. Korotin, A., Khromov, N., Stepanov, A., Lange, A., Burnaev, E., and Somov, A. (2019, January 19–23). Towards understanding of esports athletes’ potentialities: The sensing system for data collection and analysis. Proceedings of the 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), Leicester, UK.10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00319 ↗
17. Fei, Y. (2024, January 9–11). Quantitative Evaluation of Predictive Analytics: A Comparative Study of Machine Learning Models in eSports Outcome Forecasting. Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024), Singapore.
18. GgViz: Accelerating large-scale esports game analysis10.1145/3549501 ↗
19. Urbanek, J., Fan, A., Karamcheti, S., Jain, S., Humeau, S., Dinan, E., Rocktäschel, T., Kiela, D., Szlam, A., and Weston, J. (2019, January 3–7). Learning to Speak and Act in a Fantasy Text Adventure Game. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.10.18653/v1/D19-1062 ↗
20. Park, J.S., O’Brien, J., Cai, C.J., Morris, M.R., Liang, P., and Bernstein, M.S. (November, January 29). Generative agents: Interactive simulacra of human behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, San Francisco, CA, USA.
21. Ranella, N., and Eger, M. (2023, January 10–11). Towards Automated Video Game Commentary Using Generative AI. Proceedings of the EXAG@ AIIDE, Salt Lake City, UT, USA.
22. Todd, G., Earle, S., Nasir, M.U., Green, M.C., and Togelius, J. (2023, January 12–14). Level generation through large language models. Proceedings of the 18th International Conference on the Foundations of Digital Games, Lisbon, Portugal.10.1145/3582437.3587211 ↗
23. Large language models play starcraft ii: Benchmarks and a chain of summarization approach
24. Valve Corporation (2025, June 23). Dota 2. Available online: https://www.dota2.com/.
25. Riot Games (2025, June 23). Valorant. Available online: https://playvalorant.com/.
26. Valve Corporation (2025, June 23). Counter-Strike. Available online: https://csonline.nexon.com/.
27. Blizzard Entertainment (2025, June 23). Overwatch. Available online: https://playoverwatch.com/.
28. PS Analytics (2025, June 23). LOL.PS. Available online: https://lol.ps/.
29. OpenAI (2025, June 23). o200k_base Tokenizer. Available online: https://github.com/openai/tiktoken.
30. OpenAI (2025, June 23). cl100k_base Tokenizer. Available online: https://github.com/openai/tiktoken.