Interactive Storytelling: A Player Modelling Approach

Abstract

In recent years, the fields of Interactive Storytelling and Player Modelling have independently enjoyed increased interest in both academia and the computer games industry. The combination of these technologies, however, remains largely unexplored. In this paper, we present PaSSAGE (Player-Specific Stories via Automatically Generated Events), an interactive storytelling system that uses player modelling to automatically learn a model of the player's preferred style of play, and then uses that model to dynamically select the content of an interactive story. Results from a user study evaluating the entertainment value of adaptive stories created by our system as well as two fixed, pre-authored stories indicate that automatically adapting a story based on learned player preferences can increase the enjoyment of playing a computer role-playing game for certain types of players.

Telling Interactive Player-specific Stories and Planning for It: ASD + PaSSAGE = PAST

“…An alternative is to explicitly model the player and choose the most appropriate quests/story fragments for them behind the scenes (Thue et al 2007). Continuing with our example, such an AI system may infer that a player is inclined to play as a fighter and thus replace the deceased wolf with a bigger and meaner wolf.…”

“…Around the same time, a system called Player-Specific Stories via Automatically Generated Events (PaSSAGE) (Thue et al 2007) was proposed, which used AI techniques to model the player as he/she experiences a narrative-rich video game. Such a continuously updated player model was used to dynamically adapt the story, tailoring it to the current player.…”

PAStE: A Platform for Adaptive Storytelling with Events

“…This area has been well studied, and a number of techniques exist for designing effective directors. Facade (Mateas and Stern 2003) executes authored beats to manage the intensity of the story, Mimesis (Riedl, Saretto, and Young 2003) employs narrative planning (Li and Riedl 2011) with atomic agent actions, Thespian (Si, Marsella, and Pynadath 2005) uses decision-theoretic agents to create actors with social awareness, while PaSSAGE (Thue et al 2007) and the Automated Story Director (Riedl et al 2008) monitor a user's experience through the story to choose between scenes and character behavior. Riedl and Bulitko provide a more detailed survey (Riedl and Bulitko 2013) of the current work in interactive narrative.…”

“…This dramatically reduces the granularity of a narrative action sequence into more conceptually relevant atoms, and each event can be analyzed for narrative cost and effect before being made available. Because events represent temporary interactions, and many events can operate simultaneously in a world, they occupy a theoretical ground between atomic character actions, and full scenes or encounters (Thue et al 2007).…”

Mutual Implicit Question Answering for Shared Authorship: A Pilot Study on Player Expectations

“…Many interactive narrative systems are similar in spirit to one of these two non-interactive pioneers because they tend to first consider either player freedom or author control. Approaches emphasizing player freedom often use a predict-and-support strategy (Thue et al 2007;Sharma et al 2007;Rowe et al 2011). The system predicts the player's trajectory using goal recognition or a learned model of the player's preferences.…”