Working Backwards: Creating a Character Backstory Generation System Using Idealized Creative Writing Outputs

Lynda Clark (Lead / Corresponding author), Divij Sood (Lead / Corresponding author)

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


This paper is a reflection on the process of designing and developing a character backstory generation system prototype following literary analysis of idealized textual outputs. An overview of previous generative systems (both academic and commercial) and some of the design priorities associated with these systems is described in order to set a context for the project. The design process is then described, with particular focus on the creation of the idealized outputs and their purpose. Finally, the learning outcomes following initial generative texts created by the prototype engine are shared, weighing the pros and cons of both the design approach, the resulting generator and its outputs.
Original languageEnglish
Title of host publicationFDG'22
Subtitle of host publicationProceedings of the 17th International Conference on the Foundations of Digital Games
EditorsKostas Karpouzis, Stefano Gualeni, Johanna Pirker, Allan Fowler
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Number of pages9
ISBN (Electronic)9781450397957
ISBN (Print)9781450397957
Publication statusPublished - 4 Nov 2022

Publication series

NameACM International Conference Proceeding Series


  • Applied computing - Arts and Humanities
  • Text generation
  • narrative design
  • creative writing
  • literary analysis

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications


Dive into the research topics of 'Working Backwards: Creating a Character Backstory Generation System Using Idealized Creative Writing Outputs'. Together they form a unique fingerprint.

Cite this