Generating Stories Using Role-playing Games and Simulated Human-like Conversations

Abstract

Tabletop role-playing games (RPGs) have a well-tested history of making possible the improvisation of a story through the players' interactions. Adapting these human dynamics and game setting and mechanics could represent a new and fertile approach to computational story generation. In this paper we introduce a story generation system that recreates the player interaction sequence that takes place in a tabletop role-playing game (essentially a human storyteller and a player character conversation). We then process these interactions to render a story following the rules and using the knowledge base from a popular RPG. Finally, we control parameters present in the narrative RPG ruleset to tweak the resulting story, such as the presence of mental, physical and social challenges, as well as the amount of protagonism that each player has.

The Propaganda Machine: Generating Biased Reports about Risk Games

“…Gervás [10] proposes a computational model for "storifying" the events of a game of chess, considering each piece as an actor with an incomplete view of the board and finding narrative threads that could describe the movement of the pieces; while the domain of chess might include even elements of suspense [11], these works are focusing on the content determination step, without producing a linguistic output (as opposed to [12], where the goal is to simply generating linguistic explanation for the piece movements, without specific narrative qualities). Also connected to our work is [13], where a system is using the ruleset of a role-playing game to simulate the interaction between two humans (the "Master of Ceremonies", i.e. the storyteller, and a player) and an NLG module converts them into text.…”

Narrative Generation in the Wild: Methods from NaNoGenMo

“…The rule system of role-playing game Dungeons & Dragons is the most well-known of its kind. Various story and quest generation systems (Martens, 2015;Tapscott et al, 2018;Kybartas and Verbrugge, 2014) have been built upon this and other related rule systems.…”