automated continuity analysis, continuity editing, syntactic patterns, subject identification techniques, named entity recognition, coreferent resolution, proofreading
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 algorithms developed to identify sentence subjects and descriptions, to promising results. With the fragmented, iterative cycle of writing long-form prose and the limitations of human memory and reading speed, maintaining a clear and consistent image of a character's appearance and personality is a difficult task for human authors and editors to complete manually. The results of this research provide a starting point to automate and improve the process writing and proofreading narrative works.
Faculty of Applied Science & Technology
© Samantha Akulick
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Original Publication Citation
Akulick, S.(2019). Automatic description: A novel approach to documenting character description for consistency in long – form prose (Unpublished thesis). Sheridan College, Ontario, Canada.
Akulick, Samantha, "Automatic Description: A Novel Approach to Documenting Character Description for Consistency in Long – Form Prose" (2019). Faculty of Applied Science and Technology - Exceptional Student Work, Applied Computing Theses. 5.