Who wrote 'The World of Saddam Hussein?' A supervised machine learning approach.
Saved in:
| Title: | Who wrote 'The World of Saddam Hussein?' A supervised machine learning approach. |
|---|---|
| Authors: | Mohamed, Emad1 (AUTHOR) |
| Source: | Digital Scholarship in the Humanities. Apr2025, Vol. 40 Issue 1, p241-252. 12p. |
| Subjects: | World of Saddam Hussein, The (Book), Supervised learning, Anonyms & pseudonyms, Compound words, Critics |
| Abstract: | The 2003 novel 'The World of Saddam Hussein' (TWOSH), published under the pseudonym Mahdy Haidar, has long concealed the true identity of its author. This study compiles the works of eight authors previously speculated by literary critics as potential authors. Using a supervised machine learning approach with a large set of classification algorithms, I employed two distinct feature sets: (1) top frequent words and (2) top free-occurring function word compounds lacking lexical attachments. My findings suggest that (1) the author of TWOSH can be discovered with high certainty and (2) the innovative method of utilizing top free-standing function word compounds proves nearly as effective as the traditional top N words approach, offering two key advantages: the exclusion of lexical items, providing a more accurate reflection of authorial style, and the elimination of the expensive and inaccurate morphological segmentation requirement. [ABSTRACT FROM AUTHOR] |
| Copyright of Digital Scholarship in the Humanities is the property of Oxford University Press / USA and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | The 2003 novel 'The World of Saddam Hussein' (TWOSH), published under the pseudonym Mahdy Haidar, has long concealed the true identity of its author. This study compiles the works of eight authors previously speculated by literary critics as potential authors. Using a supervised machine learning approach with a large set of classification algorithms, I employed two distinct feature sets: (1) top frequent words and (2) top free-occurring function word compounds lacking lexical attachments. My findings suggest that (1) the author of TWOSH can be discovered with high certainty and (2) the innovative method of utilizing top free-standing function word compounds proves nearly as effective as the traditional top N words approach, offering two key advantages: the exclusion of lexical items, providing a more accurate reflection of authorial style, and the elimination of the expensive and inaccurate morphological segmentation requirement. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 2055768X |
| DOI: | 10.1093/llc/fqae080 |
