Effective Scenario Designs for Free-Text Interactive Fiction (bibtex)
by Margaret Cychosz, Andrew S. Gordon, Obiageli Odimegwu, Olivia Connolly, Jenna Bellassai, Melissa Roemmele
Abstract:
Free-text interactive fiction allows players to narrate the actions of protagonists via natural language input, which are automatically directed to appropriate storyline outcomes using natural language processing techniques. We describe an authoring platform called the Data-driven Interactive Narrative Engine (DINE), which supports free-text interactive fiction by connecting player input to authored outcomes using unsupervised text classification techniques based on text corpus statistics. We hypothesize that the coherence of the interaction, as judged by the players of a DINE scenario, is dependent on specific design choices made by the author. We describe three empirical experiments with crowdsourced subjects to investigate how authoring choices impacted the coherence of the interaction, finding that scenario design and writing style can predict significant differences.
Reference:
Effective Scenario Designs for Free-Text Interactive Fiction (Margaret Cychosz, Andrew S. Gordon, Obiageli Odimegwu, Olivia Connolly, Jenna Bellassai, Melissa Roemmele), In Proceedings of the International Conference on Interactive Digital Storytelling, Springer International Publishing, 2017.
Bibtex Entry:
@inproceedings{cychosz_effective_2017,
	address = {Funchal Madeira, Portugal},
	title = {Effective {Scenario} {Designs} for {Free}-{Text} {Interactive} {Fiction}},
	url = {https://link.springer.com/chapter/10.1007/978-3-319-71027-3_2},
	doi = {10.1007/978-3-319-71027-3_2},
	abstract = {Free-text interactive fiction allows players to narrate the actions of protagonists via natural language input, which are automatically directed to appropriate storyline outcomes using natural language processing techniques. We describe an authoring platform called the Data-driven Interactive Narrative Engine (DINE), which supports free-text interactive fiction by connecting player input to authored outcomes using unsupervised text classification techniques based on text corpus statistics. We hypothesize that the coherence of the interaction, as judged by the players of a DINE scenario, is dependent on specific design choices made by the author. We describe three empirical experiments with crowdsourced subjects to investigate how authoring choices impacted the coherence of the interaction, finding that scenario design and writing style can predict significant differences.},
	booktitle = {Proceedings of the {International} {Conference} on {Interactive} {Digital} {Storytelling}},
	publisher = {Springer International Publishing},
	author = {Cychosz, Margaret and Gordon, Andrew S. and Odimegwu, Obiageli and Connolly, Olivia and Bellassai, Jenna and Roemmele, Melissa},
	month = nov,
	year = {2017},
	keywords = {Narrative, UARC},
	pages = {12--23}
}
Powered by bibtexbrowser