Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner

<p>Authorship discrimination is the task of detecting whether two writings are authored by the same person. From literature study to forensic analysis, the authorship discrimination makes a significant contribution in differentiating authorship. In this work, we propose Agree-to-Disagree (A2D)...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Md. Tawkat Islam Khondaker (16870107) (author)
مؤلفون آخرون: Junaed Younus Khan (16870110) (author), Tanvir Alam (638619) (author), M. Sohel Rahman (12056885) (author)
منشور في: 2020
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513561256001536
author Md. Tawkat Islam Khondaker (16870107)
author2 Junaed Younus Khan (16870110)
Tanvir Alam (638619)
M. Sohel Rahman (12056885)
author2_role author
author
author
author_facet Md. Tawkat Islam Khondaker (16870107)
Junaed Younus Khan (16870110)
Tanvir Alam (638619)
M. Sohel Rahman (12056885)
author_role author
dc.creator.none.fl_str_mv Md. Tawkat Islam Khondaker (16870107)
Junaed Younus Khan (16870110)
Tanvir Alam (638619)
M. Sohel Rahman (12056885)
dc.date.none.fl_str_mv 2020-09-03T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2020.3021658
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Agree-to-Disagree_A2D_A_Deep_Learning-Based_Framework_for_Authorship_Discrimination_Task_in_Corpus-Specificity_Free_Manner/24016149
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Data management and data science
Machine learning
Language, communication and culture
Linguistics
Task analysis
Writing
Machine learning
Forensics
Electronic mail
Computer science
Natural language processing
Authorship discrimination
Deep learning
Neural networks
dc.title.none.fl_str_mv Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Authorship discrimination is the task of detecting whether two writings are authored by the same person. From literature study to forensic analysis, the authorship discrimination makes a significant contribution in differentiating authorship. In this work, we propose Agree-to-Disagree (A2D), a novel framework for the authorship discrimination task. It is a two-stage deep learning-based framework consisting of an `Agree' and a `Disagree' network. At the first stage, it learns the authorship attributes with its Agree network. Subsequently, through its Disagree network, the framework attempts to differentiate the authorship of a new dataset (completely unrelated to the training dataset), a novel use case that has not been systematically considered hitherto in the literature. We show that A2D is not dependent on the dataset-specific prior knowledge and it can learn only from authorship attributes of the dataset to detect whether two different writings are from the same author. We prove that the A2D framework can successfully reveal the authorship with pseudonyms through tasking it with unfolding the pseudonyms of a famous American short story writer Washington Irving. We also apply our framework on a historical topic of ascertaining whether the authorship of the most respected book in Islam (the Holy Quran) can be attributed to the Prophet of Islam. Through the experimental analysis, A2D reveals that the Prophet of Islam is not the author of the Holy Quran, and this result is in perfect alignment with the belief of 1.8 billion Muslims around the globe regarding the authorship of this holy book.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.3021658" target="_blank">https://dx.doi.org/10.1109/access.2020.3021658</a></p>
eu_rights_str_mv openAccess
id Manara2_cb8d7682afe60d5f155f981cbee0d582
identifier_str_mv 10.1109/access.2020.3021658
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24016149
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free MannerMd. Tawkat Islam Khondaker (16870107)Junaed Younus Khan (16870110)Tanvir Alam (638619)M. Sohel Rahman (12056885)Information and computing sciencesArtificial intelligenceData management and data scienceMachine learningLanguage, communication and cultureLinguisticsTask analysisWritingMachine learningForensicsElectronic mailComputer scienceNatural language processingAuthorship discriminationDeep learningNeural networks<p>Authorship discrimination is the task of detecting whether two writings are authored by the same person. From literature study to forensic analysis, the authorship discrimination makes a significant contribution in differentiating authorship. In this work, we propose Agree-to-Disagree (A2D), a novel framework for the authorship discrimination task. It is a two-stage deep learning-based framework consisting of an `Agree' and a `Disagree' network. At the first stage, it learns the authorship attributes with its Agree network. Subsequently, through its Disagree network, the framework attempts to differentiate the authorship of a new dataset (completely unrelated to the training dataset), a novel use case that has not been systematically considered hitherto in the literature. We show that A2D is not dependent on the dataset-specific prior knowledge and it can learn only from authorship attributes of the dataset to detect whether two different writings are from the same author. We prove that the A2D framework can successfully reveal the authorship with pseudonyms through tasking it with unfolding the pseudonyms of a famous American short story writer Washington Irving. We also apply our framework on a historical topic of ascertaining whether the authorship of the most respected book in Islam (the Holy Quran) can be attributed to the Prophet of Islam. Through the experimental analysis, A2D reveals that the Prophet of Islam is not the author of the Holy Quran, and this result is in perfect alignment with the belief of 1.8 billion Muslims around the globe regarding the authorship of this holy book.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.3021658" target="_blank">https://dx.doi.org/10.1109/access.2020.3021658</a></p>2020-09-03T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2020.3021658https://figshare.com/articles/journal_contribution/Agree-to-Disagree_A2D_A_Deep_Learning-Based_Framework_for_Authorship_Discrimination_Task_in_Corpus-Specificity_Free_Manner/24016149CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240161492020-09-03T00:00:00Z
spellingShingle Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner
Md. Tawkat Islam Khondaker (16870107)
Information and computing sciences
Artificial intelligence
Data management and data science
Machine learning
Language, communication and culture
Linguistics
Task analysis
Writing
Machine learning
Forensics
Electronic mail
Computer science
Natural language processing
Authorship discrimination
Deep learning
Neural networks
status_str publishedVersion
title Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner
title_full Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner
title_fullStr Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner
title_full_unstemmed Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner
title_short Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner
title_sort Agree-to-Disagree (A2D): A Deep Learning-Based Framework for Authorship Discrimination Task in Corpus-Specificity Free Manner
topic Information and computing sciences
Artificial intelligence
Data management and data science
Machine learning
Language, communication and culture
Linguistics
Task analysis
Writing
Machine learning
Forensics
Electronic mail
Computer science
Natural language processing
Authorship discrimination
Deep learning
Neural networks