Abstract
This paper presents a novel method that utilizes ChatGPT for the categorization of audience comments in game live streams, treating it as a zero-shot task. Audience participation games have gained significant popularity in the realm of game live streaming, playing a vital role in game promotion and audience engagement. Streamers employ various techniques such as storytelling and interactive narrative to cultivate a larger fan base and enhance the value of their streams. Simultaneously, the audience generates diverse comments that directly impact the streamer’s interactive narrative and storytelling. However, the traditional methods for comment analysis in game live streams are lacking in terms of speed and cost-effectiveness. Therefore, our aim is to investigate whether ChatGPT can fulfill these requirements. Through experimental evaluation, our results indicate a majority choice of 54.34% and a human choice of 82.61%, showcasing that ChatGPT, when employed with suitable prompts, can address the aforementioned need.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Seering, J.: Audience participation games: blurring the line between player and spectator. In: Proceedings of the 2017 Conference on Designing Interactive Systems, pp. 429–440 (2017)
Gallist, N., Lattner, M., Lankes, M., Hagler, J.: Build your world-meaningful choices in a hybrid stage play. In: Interactive Storytelling: 15th International Conference on Interactive Digital Storytelling, ICIDS 2022, Santa Cruz, CA, USA, 4–7 December 2022, Proceedings, pp. 697–704. Springer (2022). https://doi.org/10.1007/978-3-031-22298-6_45
Roth, C., Koenitz, H.: Bandersnatch, yea or nay? reception and user experience of an interactive digital narrative video. In: Proceedings of the 2019 ACM International Conference on Interactive Experiences for TV and Online Video, pp. 247–254 (2019)
Liu, Y., et al.: Summary of chatgpt/gpt-4 research and perspective towards the future of large language models. arXiv preprint arXiv:2304.01852 (2023)
Van Dis, E.A., Bollen, J., Zuidema, W., van Rooij, R., Bockting, C.L.: Chatgpt: five priorities for research. Nature 614(7947), 224–226 (2023)
Nov, O., Singh, N., Mann, D.M.: Putting chatgpt’s medical advice to the (turing) test. medRxiv, pp. 2023–01 (2023)
Wei, J.: et al. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)
Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)
Min, S., et al.: Rethinking the role of demonstrations: what makes in-context learning work? arXiv preprint arXiv:2202.12837 (2022)
Lanzi, P.L., Loiacono, D.: Chatgpt and other large language models as evolutionary engines for online interactive collaborative game design. arXiv preprint arXiv:2303.02155 (2023)
Biswas, S.: Role of chatgpt in gaming: According to chatgpt. Available at SSRN 4375510 (2023)
Liu, P., Yuan, W., Jinlan, F., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1–35 (2023)
Taveekitworachai, P., Abdullah, F., Dewantoro, M.F., Thawonmas, R., Togelius, J., Renz, J.: Chatgpt4pcg competition: character-like level generation for science birds. arXiv preprint arXiv:2303.15662 (2023)
Koenitz, H.: Towards a specific theory of interactive digital narrative. In: Interactive digital narrative, pp. 91–105. Routledge (2015)
Wei, Z., Wang, S., Thawonmas, R.: Difference in perceived similarity between humans and machines. Art Research 22, 2 (2022)
Li, X., Wira, M., Thawonmas, R.: Toward dynamic difficulty adjustment with audio cues by gaussian process regression in a first-person shooter. In: Entertainment Computing-ICEC 2022: 21st IFIP TC 14 International Conference, ICEC 2022, Bremen, Germany, 1–3 November 2022, Proceedings, pp. 154–161. Springer, 2022. https://doi.org/10.1007/978-3-031-20212-4_12
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, X., You, X., Chen, S., Taveekitworachai, P., Thawonmas, R. (2023). Analyzing Audience Comments: Improving Interactive Narrative with ChatGPT. In: Holloway-Attaway, L., Murray, J.T. (eds) Interactive Storytelling. ICIDS 2023. Lecture Notes in Computer Science, vol 14384. Springer, Cham. https://doi.org/10.1007/978-3-031-47658-7_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-47658-7_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47657-0
Online ISBN: 978-3-031-47658-7
eBook Packages: Computer ScienceComputer Science (R0)