Interactive Storytelling over Document Collections

TL;DR

This paper introduces an interactive storytelling method over document collections that allows users to guide story construction through constraints, leveraging topic-based distance measures and linear inequalities to improve relevance and user control.

Contribution

It presents a novel interactive storytelling framework using topic-based distances and constraint-based path selection, enabling user-guided story creation.

Findings

Effective user-guided story construction demonstrated

Improved relevance through topic-based distance measures

Flexible constraint-based path optimization

Abstract

Storytelling algorithms aim to 'connect the dots' between disparate documents by linking starting and ending documents through a series of intermediate documents. Existing storytelling algorithms are based on notions of coherence and connectivity, and thus the primary way by which users can steer the story construction is via design of suitable similarity functions. We present an alternative approach to storytelling wherein the user can interactively and iteratively provide 'must use' constraints to preferentially support the construction of some stories over others. The three innovations in our approach are distance measures based on (inferred) topic distributions, the use of constraints to define sets of linear inequalities over paths, and the introduction of slack and surplus variables to condition the topic distribution to preferentially emphasize desired terms over others. We describe experimental results to illustrate the effectiveness of our interactive storytelling approach over multiple text datasets.