IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v10y2022i5p838-d765407.html
   My bibliography  Save this article

Parallel Stylometric Document Embeddings with Deep Learning Based Language Models in Literary Authorship Attribution

Author

Listed:
  • Mihailo Škorić

    (Faculty of Mining and Geology, University of Belgrade, Djusina 7, 11120 Belgrade, Serbia)

  • Ranka Stanković

    (Faculty of Mining and Geology, University of Belgrade, Djusina 7, 11120 Belgrade, Serbia)

  • Milica Ikonić Nešić

    (Faculty of Philology, University of Belgrade, Studentski Trg 3, 11000 Belgrade, Serbia)

  • Joanna Byszuk

    (Institute of Polish Language, Polish Academy of Sciences, al. Mickiewicza 31, 31-120 Kraków, Poland)

  • Maciej Eder

    (Institute of Polish Language, Polish Academy of Sciences, al. Mickiewicza 31, 31-120 Kraków, Poland)

Abstract

This paper explores the effectiveness of parallel stylometric document embeddings in solving the authorship attribution task by testing a novel approach on literary texts in 7 different languages, totaling in 7051 unique 10,000-token chunks from 700 PoS and lemma annotated documents. We used these documents to produce four document embedding models using Stylo R package (word-based, lemma-based, PoS-trigrams-based, and PoS-mask-based) and one document embedding model using mBERT for each of the seven languages. We created further derivations of these embeddings in the form of average, product, minimum, maximum, and l 2 norm of these document embedding matrices and tested them both including and excluding the mBERT-based document embeddings for each language. Finally, we trained several perceptrons on the portions of the dataset in order to procure adequate weights for a weighted combination approach. We tested standalone (two baselines) and composite embeddings for classification accuracy, precision, recall, weighted-average, and macro-averaged F 1 -score, compared them with one another and have found that for each language most of our composition methods outperform the baselines (with a couple of methods outperforming all baselines for all languages), with or without mBERT inputs, which are found to have no significant positive impact on the results of our methods.

Suggested Citation

  • Mihailo Škorić & Ranka Stanković & Milica Ikonić Nešić & Joanna Byszuk & Maciej Eder, 2022. "Parallel Stylometric Document Embeddings with Deep Learning Based Language Models in Literary Authorship Attribution," Mathematics, MDPI, vol. 10(5), pages 1-27, March.
  • Handle: RePEc:gam:jmathe:v:10:y:2022:i:5:p:838-:d:765407
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/10/5/838/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/10/5/838/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Akimushkin, Camilo & Amancio, Diego R. & Oliveira, Osvaldo N., 2018. "On the role of words in the network structure of texts: Application to authorship attribution," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 495(C), pages 49-58.
    2. Efstathios Stamatatos, 2009. "A survey of modern authorship attribution methods," Journal of the American Society for Information Science and Technology, Association for Information Science & Technology, vol. 60(3), pages 538-556, March.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Florentina Hristea & Cornelia Caragea, 2022. "Preface to the Special Issue “Natural Language Processing (NLP) and Machine Learning (ML)—Theory and Applications”," Mathematics, MDPI, vol. 10(14), pages 1-5, July.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Nils-Axel M?rner, 2018. "Evaluation of the Performance and Efficiency of the Automated Linguistic Features for Author Identification in Short Text Messages Using Different Variable Selection Techniques," Studies in Media and Communication, Redfame publishing, vol. 6(2), pages 83-102, December.
    2. Maryam Ebrahimpour & Tālis J Putniņš & Matthew J Berryman & Andrew Allison & Brian W-H Ng & Derek Abbott, 2013. "Automated Authorship Attribution Using Advanced Signal Classification Techniques," PLOS ONE, Public Library of Science, vol. 8(2), pages 1-12, February.
    3. Diego R Amancio, 2015. "Probing the Topological Properties of Complex Networks Modeling Short Written Texts," PLOS ONE, Public Library of Science, vol. 10(2), pages 1-17, February.
    4. Sanda-Maria Avram & Mihai Oltean, 2022. "A Comparison of Several AI Techniques for Authorship Attribution on Romanian Texts," Mathematics, MDPI, vol. 10(23), pages 1-35, December.
    5. Ballandonne, Matthieu & Cersosimo, Igor, 2022. "Towards a “Text as Data” Approach in the History of Economics: An Application to Adam Smith’s Classics," OSF Preprints mg3zb, Center for Open Science.
    6. Malik Muhammad Saad Missen & Sajeeha Qureshi & Nadeem Salamat & Nadeem Akhtar & Hina Asmat & Mickaël Coustaty & V. B. Surya Prasath, 2020. "Scientometric analysis of social science and science disciplines in a developing nation: a case study of Pakistan in the last decade," Scientometrics, Springer;Akadémiai Kiadó, vol. 123(1), pages 113-142, April.
    7. Matthew J. Schneider & Shawn Mankad, 2021. "A Two-Stage Authorship Attribution Method Using Text and Structured Data for De-Anonymizing User-Generated Content," Customer Needs and Solutions, Springer;Institute for Sustainable Innovation and Growth (iSIG), vol. 8(3), pages 66-83, September.
    8. Kargin, Vladislav, 2016. "On variation of word frequencies in Russian literary texts," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 445(C), pages 328-334.
    9. Andi Rexha & Mark Kröll & Hermann Ziak & Roman Kern, 2018. "Authorship identification of documents with high content similarity," Scientometrics, Springer;Akadémiai Kiadó, vol. 115(1), pages 223-237, April.
    10. Jacques Savoy & Olena Zubaryeva, 2012. "Simple and efficient classification scheme based on specific vocabulary," Computational Management Science, Springer, vol. 9(3), pages 401-415, August.
    11. Haoran Zhu & Lei Lei, 2022. "The Research Trends of Text Classification Studies (2000–2020): A Bibliometric Analysis," SAGE Open, , vol. 12(2), pages 21582440221, April.
    12. Silvia Corbara & Alejandro Moreo & Fabrizio Sebastiani, 2023. "Syllabic quantity patterns as rhythmic features for Latin authorship attribution," Journal of the Association for Information Science & Technology, Association for Information Science & Technology, vol. 74(1), pages 128-141, January.
    13. Oleg Sobchuk & Artjoms Šeļa, 2024. "Computational thematics: comparing algorithms for clustering the genres of literary fiction," Palgrave Communications, Palgrave Macmillan, vol. 11(1), pages 1-12, December.
    14. Jennifer A. Byrne & Cyril Labbé, 2017. "Striking similarities between publications from China describing single gene knockdown experiments in human cancer cell lines," Scientometrics, Springer;Akadémiai Kiadó, vol. 110(3), pages 1471-1493, March.
    15. de Arruda, Henrique F. & Marinho, Vanessa Q. & Lima, Thales S. & Amancio, Diego R. & Costa, Luciano da F., 2018. "An image analysis approach to text analytics based on complex networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 510(C), pages 110-120.
    16. Stefano Sbalchiero & Maria Stella Righettini, 2017. "Rhetorical manifestation of institutional transformation," Quality & Quantity: International Journal of Methodology, Springer, vol. 51(3), pages 1279-1296, May.
    17. Matilde Trevisani & Arjuna Tuzzi, 2015. "A portrait of JASA: the History of Statistics through analysis of keyword counts in an early scientific journal," Quality & Quantity: International Journal of Methodology, Springer, vol. 49(3), pages 1287-1304, May.
    18. Christian-Daniel Curiac & Alex Doboli & Daniel-Ioan Curiac, 2022. "Co-Occurrence-Based Double Thresholding Method for Research Topic Identification," Mathematics, MDPI, vol. 10(17), pages 1-10, August.
    19. Catalin Stoean & Daniel Lichtblau, 2020. "Author Identification Using Chaos Game Representation and Deep Learning," Mathematics, MDPI, vol. 8(11), pages 1-18, November.
    20. Ahmed Shamsul Arefin & Renato Vimieiro & Carlos Riveros & Hugh Craig & Pablo Moscato, 2014. "An Information Theoretic Clustering Approach for Unveiling Authorship Affinities in Shakespearean Era Plays and Poems," PLOS ONE, Public Library of Science, vol. 9(10), pages 1-12, October.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:10:y:2022:i:5:p:838-:d:765407. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.