BRANCHES: A Dataset and Analysis of Narrative Graphs in Visual Novels

• Giovanni Carbinatti Instituto de Pesquisas Eldorado
• Wandemberg Santana Pharaoh Gibaut Instituto de Pesquisas Eldorado

DOI: https://doi.org/10.5753/sbgames.2026.24056

Resumo

Introduction: Interactive narratives in visual novels present complex branching structures that remain difficult to analyze systematically at scale. Despite the widespread use of the Ren’Py engine, there is a lack of standardized datasets enabling computational analysis of such structures. Objective: This work introduces BRANCHES, a dataset of narrative graphs extracted from visual novels, aiming to support large-scale analysis of interactive storytelling. Methodology: We collected 592 publicly available visual novel projects and implemented a static analysis pipeline to parse script files, extracting narrative nodes, transitions, and player choices. Each project is represented as a directed graph, and structural metrics such as branching factor and choice density are computed. Results: The dataset reveals a wide spectrum of narrative structures, with most projects exhibiting near-linear progression (median branching factor of 1.31) and a small subset showing highly complex branching (up to 20.32). The number of choices ranges from 0 to 3303, indicating substantial variability in interactivity. These findings show that visual novels span from simple linear narratives to highly interactive structures, demonstrating the potential of the dataset for large-scale analysis.

Palavras-chave: Interactive Narrative, Visual Novels, Narrative Graphs, Static Analysis, Dataset

Referências

Allen, F. E. (1970). Control flow analysis. ACM Sigplan Notices, 5(7):1–19.

Camingue, J., Carstensdottir, E., e Melcer, E. F. (2021). What is a visual novel? Proceedings of the ACM on Human-Computer Interaction, 5(CHI PLAY):1–18.

Danescu-Niculescu-Mizil, C. e Lee, L. (2011). Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs. In Proceedings of the 2nd workshop on cognitive modeling and computational linguistics, pages 76–87.

Drachen, A., Thurau, C., Togelius, J., Yannakakis, G. N., e Bauckhage, C. (2013). Game data mining. In Game analytics: Maximizing the value of player data, pages 205–253. Springer.

GitHub, Inc. Github: Where the world builds software. [link]. Accessed: 2026-03-21.

itch.io. itch.io: Open marketplace for independent digital creators. [link]. Accessed: 2026-03-21.

Kybartas, B. e Bidarra, R. (2016). A survey on story generation techniques for authoring computational narratives. IEEE Transactions on Computational Intelligence and AI in Games, 9(3):239–253.

Mateas, M. e Stern, A. (2003). Façade: An experiment in building a fully-realized interactive drama. In Game developers conference, volume 2, pages 4–8.

Mostafazadeh, N., Chambers, N., He, X., Parikh, D., Batra, D., Vanderwende, L., Kohli, P., e Allen, J. (2016). A corpus and cloze evaluation for deeper understanding of commonsense stories. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 839–849.

Murray, J. H. (2017). Hamlet on the Holodeck, updated edition: The Future of Narrative in Cyberspace. MIT press.

Ren’Py Team (2004). Ren’py visual novel engine. [link]. Accessed: 2026-03-21.

Riedl, M. O. e Young, R. M. (2010). Narrative planning: Balancing plot and character. Journal of Artificial Intelligence Research, 39:217–268.

Young, R. M., Ware, S. G., Cassell, B. A., e Robertson, J. (2013). Plans and planning in narrative generation: a review of plan-based approaches to the generation of story, discourse and interactivity in narratives. Sprache und Datenverarbeitung, Special Issue on Formal and Computational Models of Narrative, 37(1-2):41–64.

Zhu, Y., Kiros, R., Zemel, R., Salakhutdinov, R., Urtasun, R., Torralba, A., e Fidler, S. (2015). Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. In Proceedings of the IEEE international conference on computer vision, pages 19–27.