A Yorkshire Tragedy: Using Agent-Based Modeling to Suggest Authorship

以代理人基模擬法進行作者辨別之研究：以《約克郡悲劇》（A Yorkshire Tragedy）為研究對象

Brian J. Kokensparger

《數位典藏與數位人文》 3期 (2019/04) Pp. 21-42

https://doi.org/10.6853/DADH.201904_3.0002

摘要

In this paper, A Yorkshire Tragedy (AYT) is used as a focus for development of an agent-based modeling application, using a Java swarm-type modeling library called Mason. This paper utilizes data generated by stylometric algorithms within the modeling application to visualize interactions and affinities, employing plays, playwrights, and theaters all as agents against a simple backdrop of Early Modern London. During whole-play analysis (WPA), though the title page of A Yorkshire Tragedy attributes authorship to Shakespeare, and first performance to the Globe, this model suggests that it certainly was not written by Shakespeare. Scene analysis (SA) of the play, employing scenes as independent agents, suggests that none of the scenes appear to be written by Shakespeare. In a Stylo© analysis of the plays reported to be first performed at the Globe theater, A Yorkshire Tragedy appears to be stylometrically similar to another anonymous play, The Merry Devil of Edmonton, and plays written by John Ford and John Webster. Further analysis with different stylometric dimensions may provide more clarity in answering this question.

關鍵字

corpus linguistics ； textual analysis ； stylometry ； author attribution ； Early Modern English drama

並列摘要

在本論文中，我們提出一種以代理人基模擬（agent-based modeling）為基礎，所發展出來的作者辨別模型。這個程式主要是利用一個名為Mason的JAVA的模型函式庫來製作。我們並且實際以《約克郡悲劇》（A Yorkshire Tragedy）的文本為對象，進行作者的辨別。本研究使用了由本程式中的文本風格分析演算法所產生的資料，來視覺化戲劇、劇作家和劇院作為代理人之間的互動與關係。雖然《約克郡悲劇》的標題頁將作者歸屬於莎士比亞，並首次在全球演出，但透過全元素分析（whole-play analysis），本研究所提出的辨析模型暗示這篇劇作確實並非出自莎士比亞之手。而以戲劇場景進行獨立分析時，也得到類似結果－沒有任一個場景被程式建議為屬於莎士比亞的創作，並且分析結果暗示主要作者可能是威廉．達維南特（William Davenant）。但考慮到威廉．達維南特據說是在《約克郡悲劇》首次製作完成的那年才出生，因此尚無定論。在未來的分析中，我們將會嘗試加入更多維度的資料，希望能為現在的疑問找到解答。

並列關鍵字

語料庫語言學 ； 文本分析 ； 文本風格分析 ； 作者辨別 ； 近代英語戲劇

參考文獻

Evert, S., Proisl, T., Vitt, T., Schöch, C., Jannidis, F., & Pielström, S. (2015). Towards a better understanding of Burrows’s Delta in literary authorship attribution. In A. Feldman, A. Kazantseva, S. Szpakowicz, & C. Koolen (Eds.), Proceedings of the Fourth Workshop on Computational Linguistics for Literature (pp. 79-88). Denver, CO: Association for Computational Linguistics. doi:10.3115/v1/W15-0709

Juola, P. (2006). Authorship attribution. Foundations and Trends in Information Retrieval, 1, 233-334. doi:10.1561/1500000005

Coughlan, S. (2012, April 25). Shakespeare’s ‘co-author’ named by Oxford scholars. BBC News. Retrieved from https://www.bbc.com/news/education-17828729

Craig, H., & Kinney, A. F. (Eds.). (2010). Shakespeare, computers, and the mystery of authorship. Cambridge, UK: Cambridge University Press.

Eder, M., Kestemont, M., & Rybicki, J. (2013). Stylometry with R: A suite of tools. In Digital Humanities 2013: Conference abstracts (pp. 487-489). Lincoln, NE: Center for Digital Research in the Humanities.