Chollakorn Nimpattanavong
ABSTRACT
This paper presents a new approach for leveraging ChatGPT in fighting game commentary generation task. Commentary generation often relies on deep learning techniques, which typically demand extensive data to achieve effectiveness. Large language models (LLMs) have become essential due to their remarkable ability to process data efficiently, thanks to their extensive training on vast datasets. Our proposed approach integrates the use of LLMs, specifically the GPT-3.5 model, for generating commentaries through the utilization of various prompts with data from the open-source fighting game, DareFightingICE. Four prompt variants are employed to assess the effectiveness of each prompt components. Objective evaluation using natural language metrics reveals that different prompt components significantly affect the generated commentaries. Additionally, subjective evaluation through a questionnaire reveals that prompts without parameter definitions received the highest preference from human evaluators. These results suggest that LLMs exhibit versatility in generating fighting game commentaries and hold promise for broader applications.
- Jordan Ashley. 2023. Best Fighting Games in 2023. https://www.esports.net/news/fighting-games/top-10-competitive-fighting-games/Google Scholar
- Som S. Biswas. 2023. Role of Chat GPT in Public Health. Annals of Biomedical Engineering 51, 5 (01 May 2023), 868–869. https://doi.org/10.1007/s10439-023-03172-7Google ScholarCross Ref
- Julien Bousquet and Myriam Ertz. 2021. eSports: Historical Review, Current State, and Future Challenges. IGI Global, USA, 1–24. https://doi.org/10.4018/978-1-7998-7300-6.ch001Google ScholarCross Ref
- Cheuk-Yiu Chan, Chun-Chuen Hui, Wan-Chi Siu, Sin-wai Chan, and H. Anthony Chan. 2022. To Start Automatic Commentary of Soccer Game with Mixed Spatial and Temporal Attention. In TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON). IEEE, Hong Kong, 1–6. https://doi.org/10.1109/TENCON55691.2022.9978078Google ScholarCross Ref
- Jari Dahmen, M. Enes Kayaalp, Matthieu Ollivier, Ayoosh Pareek, Michael T. Hirschmann, Jon Karlsson, and Philipp W. Winkler. 2023. Artificial intelligence bot ChatGPT in medical research: the potential game changer as a double-edged sword. Knee Surgery, Sports Traumatology, Arthroscopy 31, 4 (01 Apr 2023), 1187–1189. https://doi.org/10.1007/s00167-023-07355-6Google ScholarCross Ref
- Fouad El Afi and Ouiddad Smail. 2021. The Rise of Video-Game Live Streaming: Motivations and Forms of Viewer Engagement. In 2021 International Conference on Human-Computer Interaction. Springer-Verlag, USA, 156–163. https://doi.org/10.1007/978-3-030-78645-8_20Google ScholarCross Ref
- Daniel Gros, Anna Hackenholt, Piotr Zawadzki, and Brigitta Wanner. 2018. Interactions of Twitch Users and Their Usage Behavior. In Social Computing and Social Media. Technologies and Analytics: 10th International Conference, SCSM 2018, Held as Part of HCI International 2018, Las Vegas, NV, USA, July 15-20, 2018, Proceedings, Part II (Las Vegas, NV, USA). Springer-Verlag, Berlin, Heidelberg, 201–213. https://doi.org/10.1007/978-3-319-91485-5_15Google ScholarDigital Library
- Business Research Insights. 2022. Fighting Games Market Size | Trends Analysis Report 2023. https://www.businessresearchinsights.com/market-reports/fighting-games-market-101457Google Scholar
- Tatsuya Ishigaki, Goran Topic, Yumi Hamazono, Hiroshi Noji, Ichiro Kobayashi, Yusuke Miyao, and Hiroya Takamura. 2021. Generating Racing Game Commentary from Vision, Language, and Structured Data. In Proceedings of the 14th International Conference on Natural Language Generation. Association for Computational Linguistics, Aberdeen, Scotland, UK, 103–113. https://aclanthology.org/2021.inlg-1.11Google ScholarCross Ref
- Ibrahim Khan, Thai Van Nguyen, Xincheng Dai, and Ruck Thawonmas. 2022. DareFightingICE Competition: A Fighting Game Sound Design and AI Competition. In 2022 IEEE Conference on Games (CoG). IEEE, China, 478–485. https://doi.org/10.1109/CoG51982.2022.9893624Google ScholarDigital Library
- Byeong Jo Kim and Yong Suk Choi. 2020. Automatic Baseball Commentary Generation Using Deep Learning. In Proceedings of the 35th Annual ACM Symposium on Applied Computing (Brno, Czech Republic) (SAC ’20). Association for Computing Machinery, New York, NY, USA, 1056–1065. https://doi.org/10.1145/3341105.3374063Google ScholarDigital Library
- Vikram Kumaran, Jonathan Rowe, Bradford Mott, and James Lester. 2023. SceneCraft: Automating Interactive Narrative Scene Generation in Digital Games with Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 19, 1 (Oct. 2023), 86–96. https://doi.org/10.1609/aiide.v19i1.27504Google ScholarDigital Library
- Pascal Lessel, Maximilian Altmeyer, Julian Sahner, and Antonio Krüger. 2022. Streamer’s Hell - Investigating Audience Influence in Live-Streams Beyond the Game. Proc. ACM Hum.-Comput. Interact. 6, CHI PLAY, Article 252 (oct 2022), 27 pages. https://doi.org/10.1145/3549515Google ScholarDigital Library
- Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, Shudan Zhang, Xiang Deng, Aohan Zeng, Zhengxiao Du, Chenhui Zhang, Sheng Shen, Tianjun Zhang, Yu Su, Huan Sun, Minlie Huang, Yuxiao Dong, and Jie Tang. 2023. AgentBench: Evaluating LLMs as Agents. arxiv:2308.03688 [cs.AI]Google Scholar
- Feiyu Lu, Kaito Yamamoto, Luis H. Nomura, Syunsuke Mizuno, YoungMin Lee, and Ruck Thawonmas. 2013. Fighting game artificial intelligence competition platform. In 2013 IEEE 2nd Global Conference on Consumer Electronics (GCCE). IEEE, Japan, 320–323. https://doi.org/10.1109/GCCE.2013.6664844Google ScholarCross Ref
- OpenAI. 2022. Introducing ChatGPT. https://openai.com/blog/chatgptGoogle Scholar
- Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arxiv:2203.02155 [cs.CL]Google Scholar
- Brian Richards. 1987. Type/Token Ratios: what do they really tell us?Journal of child language 14 (07 1987), 201–9. https://doi.org/10.1017/S0305000900012885Google ScholarCross Ref
- Raquel Breejon Robinson, Ricardo Rheeder, Madison Klarkowski, and Regan L Mandryk. 2022. ”Chat Has No Chill”: A Novel Physiological Interaction For Engaging Live Streaming Audiences. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems (New Orleans, LA, USA) (CHI ’22). Association for Computing Machinery, New York, NY, USA, Article 562, 18 pages. https://doi.org/10.1145/3491102.3501934Google ScholarDigital Library
- Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, Karen Simonyan, Laurent Sifre, Simon Schmitt, Arthur Guez, Edward Lockhart, Demis Hassabis, Thore Graepel, Timothy Lillicrap, and David Silver. 2020. Mastering Atari, Go, chess and shogi by planning with a learned model. Nature 588, 588 (Dec 2020), 604–609. https://doi.org/10.1038/s41586-020-03051-4Google ScholarCross Ref
- Daniel Spadaro, Lawrence Robinson, and L. Smith. 1980. Assessing Readability of Patient Information Materials. American journal of hospital pharmacy 37 (03 1980), 215–21. https://doi.org/10.1093/ajhp/37.2.215Google ScholarCross Ref
- Nigar M. Shafiq Surameery and Mohammed Y. Shakor. 2023. Use Chat GPT to Solve Programming Bugs. International Journal of Information Technology & Computer Engineering (IJITC) ISSN : 2455-5290 3, 01 (Jan. 2023), 17–22. https://doi.org/10.55529/ijitc.31.17.22Google ScholarCross Ref
- Yasufumi Taniguchi, Yukun Feng, Hiroya Takamura, and Manabu Okumura. 2019. Generating Live Soccer-Match Commentary from Play Data. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence (Honolulu, Hawaii, USA) (AAAI’19/IAAI’19/EAAI’19). AAAI Press, USA, Article 871, 8 pages. https://doi.org/10.1609/aaai.v33i01.33017096Google ScholarDigital Library
- Pittawat Taveekitworachai, Febri Abdullah, Mury F. Dewantoro, Ruck Thawonmas, Julian Togelius, and Jochen Renz. 2023. ChatGPT4PCG Competition: Character-like Level Generation for Science Birds. arxiv:2303.15662 [cs.AI]Google Scholar
- Zihan Wang and Naoki Yoshinaga. 2022. Esports Data-to-commentary Generation on Large-scale Data-to-text Dataset. arxiv:2212.10935 [cs.CL]Google Scholar
- Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022. Finetuned Language Models Are Zero-Shot Learners. arxiv:2109.01652 [cs.CL]Google Scholar
- Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. Emergent Abilities of Large Language Models. Transactions on Machine Learning Research (2022). https://openreview.net/forum?id=yzkSU5zdwD Survey Certification.Google Scholar
- Piers R. Williams, Diego Perez-Liebana, and Simon M. Lucas. 2016. Ms. Pac-Man Versus Ghost Team CIG 2016 competition. In 2016 IEEE Conference on Computational Intelligence and Games (CIG). IEEE, Greece, 1–8. https://doi.org/10.1109/CIG.2016.7860446Google ScholarDigital Library
- Michal Čertický, David Churchill, Kyung-Joong Kim, Martin Čertický, and Richard Kelly. 2019. StarCraft AI Competitions, Bots, and Tournament Manager Software. IEEE Transactions on Games 11, 3 (2019), 227–237. https://doi.org/10.1109/TG.2018.2883499Google ScholarCross Ref
Index Terms
- Am I Fighting Well? Fighting Game Commentary Generation With ChatGPT
Recommendations
Exploring the Potential of ChatGPT as a Dungeon Master in Dungeons & Dragons tabletop game
IAIT '23: Proceedings of the 13th International Conference on Advances in Information TechnologyThe emergence of advanced AI language models has opened up new possibilities for the integration of artificial intelligence in various domains, including tabletop role-playing games. This research explores the potential of ChatGPT, a widely-used large ...
An interface for post-match play-by-play analysis of a fighting game based on the two players' eye movements
SA '18: SIGGRAPH Asia 2018 PostersIn this paper, we propose an interface to support post-match play-by-play analysis of a hand-to-hand fighting game based on the two players' eye movements. In the domain of e-Sports, the "fighting game" genre refers to hand-to-hand combat games in which ...
Watching Support System by Annotation Displaying According to Fighting Game Situations
Entertainment Computing – ICEC 2017AbstractThis study proposes a watching support system for a beginner watcher of fighting games. The fighting games is a type of e-Sports genre similar to Karate and boxing. Two game characters (e.g., a grappler) fight each other in the game. As with ...
Comments