This paper explores the potential of utilizing ChatGPT, a large language model (LLM), for generating and evaluating visual novel (VN) game stories in the context of global warming awareness through a VN game. The study involves generating two stories using ChatGPT, one with given global warming related keywords as an inspiration for ChatGPT along with a specified ending and another without, and evaluating them based on several linguistic criteria: coherence, inspiration, readability, word complexity, and narrative fluency. Results reveal that keywords-inspired story exhibit higher coherence, while the basic one demonstrate greater inspiration. The findings highlight the advantages of each story and emphasize the value of AI-driven narrative generation in creating engaging and informative experiences. Furthermore, the study introduces an innovative approach by employing ChatGPT as an evaluator for the story quality, by combining various prompt engineering techniques showcasing the diverse applications of LLMs in interactive storytelling. This work contributes to the growing field of LLM-based story generation and underscores the potential of AI-driven narratives in fostering awareness and engagement on critical issues like climate change.

The Chronicles of ChatGPT: Generating and Evaluating Visual Novel Narratives on Climate Change Through ChatGPT / Gursesli M.C.; Taveekitworachai P.; Abdullah F.; Dewantoro M.F.; Antonio Lanata; Guazzini A.; Le V.K.; Villars A.; Thawonmas R.. - ELETTRONICO. - 14384 LNCS:(2023), pp. 181-194. (Intervento presentato al convegno 16th International Conference on Interactive Digital Storytelling) [10.1007/978-3-031-47658-7_16].

The Chronicles of ChatGPT: Generating and Evaluating Visual Novel Narratives on Climate Change Through ChatGPT

Gursesli M. C.;Antonio Lanata;Guazzini A.;
2023

Abstract

This paper explores the potential of utilizing ChatGPT, a large language model (LLM), for generating and evaluating visual novel (VN) game stories in the context of global warming awareness through a VN game. The study involves generating two stories using ChatGPT, one with given global warming related keywords as an inspiration for ChatGPT along with a specified ending and another without, and evaluating them based on several linguistic criteria: coherence, inspiration, readability, word complexity, and narrative fluency. Results reveal that keywords-inspired story exhibit higher coherence, while the basic one demonstrate greater inspiration. The findings highlight the advantages of each story and emphasize the value of AI-driven narrative generation in creating engaging and informative experiences. Furthermore, the study introduces an innovative approach by employing ChatGPT as an evaluator for the story quality, by combining various prompt engineering techniques showcasing the diverse applications of LLMs in interactive storytelling. This work contributes to the growing field of LLM-based story generation and underscores the potential of AI-driven narratives in fostering awareness and engagement on critical issues like climate change.
2023
Interactive Storytelling
16th International Conference on Interactive Digital Storytelling
Gursesli M.C.; Taveekitworachai P.; Abdullah F.; Dewantoro M.F.; Antonio Lanata; Guazzini A.; Le V.K.; Villars A.; Thawonmas R.
File in questo prodotto:
File Dimensione Formato  
978-3-031-47658-7_16.pdf

accesso aperto

Tipologia: Pdf editoriale (Version of record)
Licenza: Open Access
Dimensione 977.17 kB
Formato Adobe PDF
977.17 kB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1346081
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact