Publikationer från Malmö universitet
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
ChatGPT as a Narrative Structure Interpreter
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT).ORCID-id: 0000-0002-7738-1601
2023 (Engelska)Ingår i: 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, s. 113-121Konferensbidrag, Publicerat paper (Refereegranskat)
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.

Ort, förlag, år, upplaga, sidor
Springer, 2023. s. 113-121
Serie
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 384
Nyckelord [en]
Narrative Structures, Large Language Models, ChatGPT, Games, Story Generation
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
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 (tryckt)ISBN: 978-3-031-47658-7 (tryckt)OAI: oai:DiVA.org:mau-64278DiVA, id: diva2:1818832
Konferens
16th International Conference on Interactive Digital Storytelling, ICIDS 2023, Kobe, Japan, November 11–15, 2023
Tillgänglig från: 2023-12-12 Skapad: 2023-12-12 Senast uppdaterad: 2023-12-12Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Alvarez, Alberto

Sök vidare i DiVA

Av författaren/redaktören
Alvarez, Alberto
Av organisationen
Institutionen för datavetenskap och medieteknik (DVMT)
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 90 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf