Abstract
Dungeons and Dragons is a tabletop roleplaying game which focuses heavily on character interaction and creating narratives. The current state of the game's character creation process often bogs down new players in decisions related to game mechanics, not a character's identity and personality. This independent study investigates the use of machine learning and natural language processing to make these decisions for a player based on their character's backstory - the textual biography or description of a character. The study presents a collection of existing characters and uses these examples to create a family of models capable of predicting a character's class, race, and attribute scores. The accuracy and limitations of these models are discussed, but they represent a first step in abstracting away some of the more tedious parts of character creation for new players.
Advisor
Sommer, Nathan
Department
Computer Science
Recommended Citation
MacInnes, Joseph C., "The D&D Sorting Hat: Predicting Dungeons and Dragons Characters from Textual Backstories" (2019). Senior Independent Study Theses. Paper 8635.
https://openworks.wooster.edu/independentstudy/8635
Disciplines
Artificial Intelligence and Robotics | Numerical Analysis and Scientific Computing
Keywords
machine learning, dungeons and dragons, natural language processing
Publication Date
2019
Degree Granted
Bachelor of Arts
Document Type
Senior Independent Study Thesis Exemplar
External Link
http://chardd.net
Included in
Artificial Intelligence and Robotics Commons, Numerical Analysis and Scientific Computing Commons
© Copyright 2019 Joseph C. MacInnes