Social and Behavioral Sciences Commons^™

Automatic Description: A Novel Approach To Documenting Character Description For Consistency In Long – Form Prose, Samantha Akulick

Faculty of Applied Science and Technology - Exceptional Student Work, Applied Computing Theses

Currently, continuity editing for narrative fiction is performed manually. Many hours of human effort are required to comb through written works for inconsistencies. This study investigates the use of syntactic patterns of descriptions in narrative text and subject identification techniques like named entity recognition (NER) and coreferent resolution in narrative text as a step toward automated continuity analysis. This investigation involved examining natural English language to identify patterns used in descriptions and using natural language processing (NLP) techniques to identify those patterns and sentence subjects programmatically. Results were assessed by using the content of well-known works of fiction and two …