Modeling Protagonist Emotions for Emotion-Aware Storytelling

TL;DR

This paper introduces models for generating stories with controlled emotional trajectories of protagonists, enhancing storytelling by aligning story content with specified emotion arcs using reinforcement learning.

Contribution

It presents the first neural storytelling methods that explicitly model and control protagonist emotions throughout the story.

Findings

Models outperform baselines in following desired emotion arcs

Emotion-reinforced models maintain story quality

Automatic and manual evaluations confirm effectiveness

Abstract

Emotions and their evolution play a central role in creating a captivating story. In this paper, we present the first study on modeling the emotional trajectory of the protagonist in neural storytelling. We design methods that generate stories that adhere to given story titles and desired emotion arcs for the protagonist. Our models include Emotion Supervision (EmoSup) and two Emotion-Reinforced (EmoRL) models. The EmoRL models use special rewards designed to regularize the story generation process through reinforcement learning. Our automatic and manual evaluations demonstrate that these models are significantly better at generating stories that follow the desired emotion arcs compared to baseline methods, without sacrificing story quality.