Plan Recognition in Stories and in Life

TL;DR

This paper explores how plan recognition differs between stories and real life by modeling the influence of objects and relevance, using Bayesian networks to formalize the theory and explain observed differences.

Contribution

It introduces a Bayesian network model capturing how object relevance affects plan recognition in stories versus real life.

Findings

A specific network parameter correlates with story-like versus life-like responses.

Relevance of facts influences plan recognition decisions.

Model explains differences in human responses to stories and real-world scenarios.

Abstract

Plan recognition does not work the same way in stories and in "real life" (people tend to jump to conclusions more in stories). We present a theory of this, for the particular case of how objects in stories (or in life) influence plan recognition decisions. We provide a Bayesian network formalization of a simple first-order theory of plans, and show how a particular network parameter seems to govern the difference between "life-like" and "story-like" response. We then show why this parameter would be influenced (in the desired way) by a model of speaker (or author) topic selection which assumes that facts in stories are typically "relevant".