Abstract
The paper concerns the authorship recognition in a collection of Polish literary texts from the late 19th and early 20th centuries, consisting of 99 novels from 33 authors. The authors divide the books into smaller parts and analyze the classification based on a book part. To mimic the real task of testing an unknown book, the data set has been divided in such a way that parts of the same book do not appear simultaneously in the training and test set. The authors compare the approaches by working with raw texts, and, to avoid the semantic features of the text, they represent texts in the form of a sequence of grammatical class bigrams. In the case of raw text analysis, classical TF-IDF, supervised fastText, and contemporary transformer-based BERT are analyzed. In the case of grammatical classes, only TF-IDF and fastText are applied. In addition, the authors propose a sequence averaging method that works by dividing the text into smaller parts, classifying each part separately, and making the final classification based on averaging results from each part of the text. The study suggests that the TF-IDF on the raw text outperforms other methods and the sequence averaging improves the classification results for most of the analyzed schemas. Surprisingly, the BERT based method is the worst. This phenomenon is carefully analyzed and explained.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alexandre, L.A., Campilho, A.C., Kamel, M.: On combining classifiers using sum and product rules. Pattern Recogn. Lett. 22(12), 1283–1289 (2001). https://doi.org/10.1016/S0167-8655(01)00073-3
Barlas, G., Stamatatos, E.: Cross-domain authorship attribution using pre-trained language models. In: Maglogiannis, I., Iliadis, L., Pimenidis, E. (eds.) AIAI 2020. IAICT, vol. 583, pp. 255–266. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49161-1_22
Calix, K., Connors, M., Levy, D., Manzar, H., McCabe, G., Westcott, S.: Stylometry for e-mail author identification and authentication (2008)
Can, M.: Authorship attribution using principal component analysis and competitive neural networks. Math. Comput. Appl. 19(1), 21–36 (2014)
Craig, H., Kinney, A.: Shakespeare, Computers, and the Mystery of Authorship. Cambridge University Press, Cambridge (2009)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Eder, M., Piasecki, M., Walkowiak, T.: Open stylometric system based on multilevel text analysis. Cogn. Stud. | Études cognitives 17 (2017). https://doi.org/10.11649/cs.1430
Eder, M., Rybicki, J.: Late 19th- and early 20th-century polish novels (2015). http://hdl.handle.net/11321/57. CLARIN-PL digital repository
Fabien, M., Villatoro-Tello, E., Motlicek, P., Parida, S.: BertAA: BERT fine-tuning for authorship attribution. In: Proceedings of the 17th International Conference on Natural Language Processing (ICON), pp. 127–137. NLP Association of India (NLPAI), Indian Institute of Technology Patna, Patna, India (2020). https://aclanthology.org/2020.icon-main.16
Grave, E., Bojanowski, P., Gupta, P., Joulin, A., Mikolov, T.: Learning word vectors for 157 languages. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018), pp. 3483–3487 (2018)
Grivas, A., Krithara, A., Giannakopoulos, G.: Author profiling using stylometric and structural feature groupings. In: Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum, Toulouse, France, 8–11 September 2015. CEUR Workshop Proceedings, vol. 1391. CEUR-WS.org (2015). http://ceur-ws.org/Vol-1391/68-CR.pdf
Harris, Z.S.: Distributional structure. Word 10(2–3), 146–162 (1954)
Hastie, T.J., Tibshirani, R.J., Friedman, J.H.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Series in Statistics, Springer, New York (2009). https://doi.org/10.1007/978-0-387-84858-7
Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pp. 427–431. Association for Computational Linguistics (2017). http://aclweb.org/anthology/E17-2068
Juola, P.: Authorship attribution. Found. Trends Inf. Retr. 1(3), 233–334 (2006). https://doi.org/10.1561/1500000005
Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: International Conference on Machine Learning, pp. 1188–1196 (2014)
Piasecki, M., Walkowiak, T., Eder, M.: Open stylometric system WebSty: Integrated language processing, analysis and visualisation. Comput. Methods Sci. Technol. 24(1), 43–58 (2018)
Przepiórkowski, A., Bańko, M., Górski, R.L., Lewandowska-Tomaszczyk, B. (eds.): Narodowy Korpus Jezyka Polskiego [Eng.: National Corpus of Polish]. Wydawnictwo Naukowe PWN (2012). http://nkjp.pl/settings/papers/NKJP_ksiazka.pdf
Radziszewski, A.: A tiered CRF tagger for Polish. In: Bembenik, R., Skonieczny, L., Rybinski, H., Kryszkiewicz, M., Niezgodka, M. (eds.) Intelligent Tools for Building a Scientific Information Platform. Studies in Computational Intelligence, vol. 467, pp. 215–230. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-35647-6_16
Rybak, P., Mroczkowski, R., Tracz, J., Gawlik, I.: KLEJ: comprehensive benchmark for polish language understanding. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1191–1201. Association for Computational Linguistics (2020). https://www.aclweb.org/anthology/2020.acl-main.111
Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513–523 (1988)
Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
Walkowiak, T.: Subject classification of texts in polish - from TF-IDF to transformers. In: Zamojski, W., Mazurkiewicz, J., Sugier, J., Walkowiak, T., Kacprzyk, J. (eds.) DepCoS-RELCOMEX 2021. AISC, vol. 1389, pp. 457–465. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-76773-0_44
Walkowiak, T., Piasecki, M.: Stylometry analysis of literary texts in polish. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2018. LNCS (LNAI), vol. 10842, pp. 777–787. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91262-2_68
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Walkowiak, T. (2023). Author Attribution of Literary Texts in Polish by the Sequence Averaging. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2022. Lecture Notes in Computer Science(), vol 13589. Springer, Cham. https://doi.org/10.1007/978-3-031-23480-4_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-23480-4_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23479-8
Online ISBN: 978-3-031-23480-4
eBook Packages: Computer ScienceComputer Science (R0)