Automatic extraction of playable narrative units coupled with level generation

Yiming Zhang

doi:10.54254/3029-0880/2025.28559

Abstract

In game design, how to balance narrative coherence and procedural level generation has always been a difficult problem. This paper proposes a method that can automatically extract playable narrative units from story texts and combine them with dynamically generated levels. This method relies on deep semantic parsing, structured segmentation and playability constraints to decompose narrative text into atomic fragments that can be transformed into interactive environments. The system design is divided into two stages: In the first stage, narrative extraction is completed through dependency relationship and discourse analysis; The second stage achieves adaptive level generation by means of constraint-driven grammar and reinforcement feedback. The experiment was based on 124,600 narrative samples from mythological, fantasy and contemporary interactive novels, generating 19,420 independent narrative units and 1,250 levels. Compared with the random concatenation and grammar branch methods, this method significantly improves in narrative coherence, diversity and playability. Specifically, the average coherence score reached 7.83 ± 0.42, which was significantly higher than 6.11 ± 0.51 of the Grammar-driven method. The narrative-mechanism correspondence index reached 0.74 ± 0.03, exceeding the current benchmark. The overall results show that the combination of narrative extraction and procedural generation can not only maintain the integrity of the story but also provide a feasible direction for the flexibility and scalability of the game.

Keywords: playable narrative units , procedural content generation , narrative extraction , level generation , interactive storytelling

Article Information

Received: 21 October 2025

Published: 28 October 2025

DOI: https://doi.org/10.54254/3029-0880/2025.28559

Article Type: Research Article

Cite this article

Zhang,Y. (2025). Automatic extraction of playable narrative units coupled with level generation. Advances in Operation Research and Production Management,4(2),59-63.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About this Volume

Volume Title: AORPM Vol.4

Part of Series: Advances in Operation Research and Production Management

ISSN: 3029-0880 (Print) / 3029-0899 (Online)

Copyright & License

[1]Zhong, Q. (2023, November). Enhancing Interactive Storytelling: A Computational Approach to Autonomously Generating Role-Playing Game Scripts with Natural Language Processing. In 2023 3rd International Signal Processing, Communications and Engineering Management Conference (ISPCEM) (pp. 714-719). IEEE.

[2]Chitnis, G., & Shaikh, T. (2024, October). StoryPlay: End-to-End 8-Bit Game Level Generation Using Large Language Models. In International Conference on Information Technology and Applications (pp. 337-346). Singapore: Springer Nature Singapore.

[3]Alhussain, A. I., & Azmi, A. M. (2021). Automatic story generation: A survey of approaches.ACM Computing Surveys(CSUR), 54(5), 1-38.

[4]Wen, Y., Huang, C., Zhou, H., Zeng, Z., Po, C. M. L., Togelius, J., ... & Earle, S. (2025). All stories are one story: Emotional arc guided procedural game level generation. arXiv preprint arXiv: 2508.02132.

[5]Kumaran, V., Rowe, J., Mott, B., & Lester, J. (2023, October). Scenecraft: Automating interactive narrative scene generation in digital games with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (Vol. 19, No. 1, pp. 86-96).

[6]Saffari, S., Dorrigiv, M., & Yaghmaee, F. (2024). Harnessing Machine Learning for Procedural Content Generation in Gaming: A Comprehensive Review.Journal of AI and Data Mining, 12(4), 583-597.

[7]Yannakakis, G. N., & Togelius, J. (2025). Procedural Content Generation by Content Type. In Artificial Intelligence and Games (pp. 287-312). Cham: Springer Nature Switzerland.

[8]Cavaliere, F. (2024). Natural language understanding for interaction with digital characters [Master’s thesis, ETH Zurich]. ETH Zurich Research Collection.

[9]Joon, L. H. (2024). Advancing Level Generation in Super Mario Bros.: A Proposal for Combining Diffusion Models with Real-Time Playability Assessment (Doctoral dissertation, Waseda University).

[10]Puchal, C. H., & López, M. J. J. P. (2021). To create a game master: a decalogue for procedural generation of interactive stories. In Image Processing and Multimedia Technology Centre. Polytechnic University of Catalonia.