Malmö University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
ChatGPT as a Narrative Structure Interpreter
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT).ORCID iD: 0000-0002-7738-1601
2023 (English)In: Interactive Storytelling: 16th International Conference on Interactive Digital Storytelling, ICIDS 2023, Kobe, Japan, November 11–15, 2023, Proceedings, Part II / [ed] Lissa Holloway-Attaway, John T. Murray, Springer, 2023, p. 113-121Conference paper, Published paper (Refereed)
Abstract [en]

Narrative structures define the skeleton of narratives and help at identifying common structures in stories, that then can be used to compare structures, define variations, and understand prototypical [structural] components. However, narrative structures are just one piece of the puzzle, their interpretation is what gives room to the stories seen in transmedia storytelling. In principle, a structure can be interpreted and developed with a myriad of stories, but requires some type of corpus to develop it further. Large language models such as ChatGPT could be employed for this task, if we are able to define a good narrative structure and give the tools to the algorithm to develop them further. For this paper, we use a narrative structure system called TropeTwist, which employs interconnected tropes as narrative structures, defining characters, conflicts, and plot devices in a relational graph, which gives raise to a set of trope micro- and meso-patterns. Using ChatGPT and through the web interface, we communicate all the possible elements to be used from TropeTwist and tasked ChatGPT to interpret them and generate stories. We describe our process and methodology to reach these interpretations, and present some of the generated stories based on a constructed narrative structure. Our results show the possibilities and limitations of using these systems and elaborate on future work to combine large language models for other tasks within narrative interpretation and generation.

Place, publisher, year, edition, pages
Springer, 2023. p. 113-121
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 384
Keywords [en]
Narrative Structures, Large Language Models, ChatGPT, Games, Story Generation
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mau:diva-64278DOI: 10.1007/978-3-031-47658-7_9Scopus ID: 2-s2.0-85177442540ISBN: 978-3-031-47657-0 (print)ISBN: 978-3-031-47658-7 (print)OAI: oai:DiVA.org:mau-64278DiVA, id: diva2:1818832
Conference
16th International Conference on Interactive Digital Storytelling, ICIDS 2023, Kobe, Japan, November 11–15, 2023
Available from: 2023-12-12 Created: 2023-12-12 Last updated: 2023-12-12Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Alvarez, Alberto

Search in DiVA

By author/editor
Alvarez, Alberto
By organisation
Department of Computer Science and Media Technology (DVMT)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 93 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf