Interactive Storytelling over Document Collections
This work addresses the need for more user-controlled storytelling in document analysis, offering an incremental improvement over existing algorithms.
The paper tackled the problem of constructing coherent stories from document collections by introducing an interactive approach where users can specify 'must use' constraints to guide story construction, resulting in a method that effectively builds stories over multiple text datasets.
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.