FAQ
logo Uniwersytetu Jagiellońskiego w Krakowie
PL | EN

Ustawienia prywatności (cookies)

Ta strona używa ciasteczek (cookies), dzięki którym nasz serwis może działać lepiej. Aby uzyskać więcej informacji i spersonalizować swoje preferencje, kliknij „Ustawienia”. W każdej chwili możesz zmienić swoje preferencje, a także cofnąć zgodę na używanie plików cookie na poniższej stronie.
Polityka prywatności (link otworzy się w nowym oknie)
* z wyjątkiem niezbędnych plików cookies do prawidłowego działania strony oraz realizacji obowiązków prawnych administratora
Przesuwając suwak w prawo aktywujesz konkretną zgodę. Przesuwając suwak w lewo wyłączasz taką zgodę.

Au-delà de l’attribution d’auteur : la stylométrie permet-elle d’identifier l’« identité collective » des textes littéraires et le sexe des auteurs ? Analyse comparée de la fiction narrative d’Europe et d’Afrique

Data publikacji: 16.12.2025

Romanica Cracoviensia, Tom 25 (2025), Tom 25, numer 3, s. 203-227

https://doi.org/10.4467/20843917RC.25.037.22750

Autorzy

,
Adam Pawłowski
Uniwersytet Wrocławski
, Polska
https://orcid.org/0000-0002-0804-5698 Orcid
Kontakt z autorem
Wszystkie publikacje autora →
,
Ewa Kalinowska
Uniwersytet Warszawski
, Polska
https://orcid.org/0000-0002-8251-2696 Orcid
Kontakt z autorem
Wszystkie publikacje autora →
Tomasz Walkowiak
Politechnika Wrocławska
, Polska
https://orcid.org/0000-0002-7749-4251 Orcid
Kontakt z autorem
Wszystkie publikacje autora →

Pobierz pełny tekst

Drukuj drukuj Cytuj cytuj

Tytuły

Au-delà de l’attribution d’auteur : la stylométrie permet-elle d’identifier l’« identité collective » des textes littéraires et le sexe des auteurs ? Analyse comparée de la fiction narrative d’Europe et d’Afrique

Abstrakt

This article reports a stylometric study of contemporary French prose from the second half of the 20th century by authors from Europe and Francophone Africa. We test whether classical stylometry, long effective in authorship attribution, can also capture collective properties of large corpora – specifically author gender and cultural origin. Results show that, in fiction, gender detection is highly unreliable: skilled writers can convincingly adopt diverse voices regardless of sociological profile, whereas the same methods often succeed on non-fiction by users (blogs, emails, social media). Likewise, in French prose, analyses based on short lists of neutral function words fail to discriminate European from African authors. Clear separation appears only when long n-gram features are used, which encode culturally inflected vocabulary and contexts. We discuss methodological implications for stylometry beyond attribution.

Informacja

Dans le cadre de cette recherche, l’infrastructure CLARIN-PL et les résultats du projet « Infrastructure de recherche numérique pour les sciences humaines et les arts DARIAHPL » ont été utilisés (POIR.04.02.00-00-D006/20-00).

Bibliografia

Pobierz bibliografię

Aravantinou Christina, Simaki Vasiliki, Mporas Iosif, Megalooikonomou Vasileios, 2015, « Gender Classification of Web Authors Using Feature Selection and Language Models », (in :), Speech and Computer: SPECOM 2015. Lecture Notes in Computer Science 9319, Andrey Ronzhin, Rodmonga Potapova, Nikos Fakotakis (eds.), Cham : Springer, 226–233, DOI : 10.1007/978-3-319-23132-7_28.

CrossRef Następne

Best Karl-Heinz, 2006, « Ernst Wilhelm Förstemann (1822–1906) », Glottometrics 12 : 77–86.

Bunjakovskij Viktor Jakovlevič, 1847, « O vozmožnosti vvedenija opredielitiel’nyx mere doverija k rezultatam nekotoryx nauk nabljudatel’nyx i preimuščestenno statistiki [Sur la possibilité d’introduire des mesures définies de confiance dans les résultats de certaines sciences observatrices et principalement statistiques] », Sovremennik 3 (2) : 36–49.

Burrows John, 2002, « “Delta”: A Measure of Stylistic Difference and a Guide to Likely Authorship », Literary and Linguistic Computing 17 (3) : 267–287, DOI : 10.1093/llc/17.3.267.

CrossRef Następne

Campello Ricardo J.G.B., Moulavi Davoud, Zimek Arthur, Sander Jörg, 2015, « Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection », ACM Transactions on Knowledge Discovery from Data (TKDD) 10 (1), Article 5, 1–51, DOI : 10.1145/2733381.

CrossRef Następne

Canut Cécile, 2010, « ‘À bas la francophonie !’ De la mission civilisatrice du français en Afrique à sa mise en discours postcoloniale », Langue française 3 (167) : 141–158.

Cheng Na, Chandramouli Rajarathnam, Subbalakshmi Koduvayur P., 2011, « Author Gender Identification from Text », Digital Investigation 8 : 78–88.

Deitrick William, Miller Zachary, Valyou Benjamin, Dickinson Brian, 2012, « Gender Prediction in an Email Stream Using Neural Networks », Journal of Intelligent Learning Systems and Applications 4 (3) : 169–175. DOI : 10.4236/jilsa.2012.43017.

CrossRef Następne

Doležel Lubomir, 1969, « A Framework for the Statistical Analysis of Style », (in :) Statistics and Style, Lubomir Doležel, Richard W. Bailey (eds.), New York : American Elevier Publishing Company, 10–25.

Eder Maciej, Rybicki Jan, Kestemont Mike, 2016, « Stylometry with R: A Package for Computational Text Analysis », The R Journal 8 (1) : 107–21, DOI : 10.32614/RJ-2016-007.

CrossRef Następne

Förstemann Ernst, 1846, « Ueber die numerischen Lautverhältnisse im Deutschen », Germania. Neues Jahrbuch der Berliner Gesellschaft für deutsche Sprache und Alterthumskunde 7 : 83–90.

Girauld Claire, Mouzard Céline (éds.), 2010, Indépendances cha-cha, Paris : Magellan & Cie; Algérie : les Éd. APIC; Côte d’Ivoire : Éburnie [etc.].

Grzybek Peter, 2003, « Viktor Jakovlevič Bunjakovskij », Glottometrics 6 : 103–104.

Kesteloot Lilyan, 2001, Histoire de la littérature négro-africaine, Paris : Karthala–AUF.

Kholoud Alsmearat, Mahmoud Al-Ayyoub, Riyad Al-Shalabi, Ghassan Kanaan, 2017, « Author Gender Identification from Arabic Text », Journal of Information Security and Applications 35 : 85–95.

Lutosławski Wincenty, 1897 [1983], The Origin and Growth of Platos Logic, London–New York–Bombay : Longmans, Green and Co. [reimpression Hildersheim : Georg Olms Verlag, 1983].

Lutosławski Wincenty, 1898, « Principes de stylométrie appliqués à la chronologie des oeuvres de Platon », Revue des Études Grecques 41 : 61–81.

Lutosławski Wincenty, 1946, « Warunki stosowania stylometrii (streszczenie wystąpienia) », Sprawozdania PAU 47 (7) : 241–242.

Luzzatto Samuel David, 2005 [1836], Prolegomena to a Grammar of the Hebrew language, Traduction Aaron D. Rubin, Piscataway, NJ : Gorgias Press [édition originale en italien en 1836].

Maaten Laurens van der, Hinton Geoffrey, 2008, « Visualizing data using t-SNE », Journal of Machine Learning Research 9 : 2579–2605.

Mahor Urmila, Kumar Aarti, 2023, « A Comparative Study of Stylometric Characteristics in Authorship Attribution », (in :) Information and Communication Technology for Competitive Strategies (ICTCS 2021): Lecture Notes in Networks and Systems, vol. 400, Amit Joshi, Mufti Mahmud, Roshan G. Ragel (eds.), Singapore : Springer, DOI : 10.1007/978-981-19-0095-2_8.

CrossRef Następne

Mcinnes Leland, Healy John, Melville James, 2018, « UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction ». arXiv preprint arXiv:1802.03426. DOI : https://arxiv.org/abs/1802.03426

Morgan Sophia Elisabeth de, 1882, Memoir of Augustus de Morgan, by His Wife Sophia Elisabeth de Morgan, with Selection of his Letters, London : Longmans, Green, and Co.

Quérard Jean-Marie, 1965 [1870–1889], Les supercheries littéraires dévoilées. Suivie 1. Du Dictionnaire des ouvrages anonymes par Ant.-Alex. Barbier, 3. Éd., revue et augmentée par Olivier Barbier, 2. Dune table générale des noms réels des écrivains anonymes et pseudonymes cités dans les deux ouvrages, Hildesheim : Olms [réimpression de la 2-ème édition, Paris 1870–1889].

Rong Zheng, Jiexun Li, Hsinchun Chen, Zan Huang, 2006, « A Framework for Authorship Identification of Online Messages : Writing-style Features and Classification Techniques », Journal of the American Society for Information Science and Technology 57 (3) : 378–393.

Salton Gerard, Buckley Christopher, 1988, « Term-weighting Approaches in Automatic Text Retrieval », Information Processing and Management 24 (5) : 513–523.

Sboev Aleksandr, Moloshnikov Ivan, Gudovskikh Dmitry, Rybka Roman, 2017, A Comparison of Data Driven Models of Solving the Task of Gender Identification of Author in Russian Language Texts for Cases without and with the Gender Deception », Journal of Physics : Conf. Series 937, IOP Publishing. DOI : 10.1088/1742-6596/937/1/012046.

CrossRef Następne

Soler-Company Juan, Wanner Leo, 2016, « A Semi-supervised Approach for Gender Identification », (in :) Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 16), Nicoletta Calzolari et al. (eds.), Portorož : European Language Resources Association, 1282–1287.

Stamatatos Efstathios, 2009, « A Survey of Modern Authorship Attribution Methods », Journal of the American Society for Information Science and Technology 60 (3) : 538–556.

Vinh Nguyen Xuan, Epps Julien, Bailey James, 2010, « Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance », Journal of Machine Learning Research 11 (95) : 2837–2854.

Yildiz Tuğba, 2019, « A Comparative Study of Author Gender Identification », Turkish Journal of Electrical Engineering & Computer Sciences 27 : 1052–1064.

Informacje

Informacje: Romanica Cracoviensia, Tom 25 (2025), Tom 25, numer 3, s. 203-227

Typ artykułu: Oryginalny artykuł naukowy

Tytuły:

Francuski: Au-delà de l’attribution d’auteur : la stylométrie permet-elle d’identifier l’« identité collective » des textes littéraires et le sexe des auteurs ? Analyse comparée de la fiction narrative d’Europe et d’Afrique
Angielski: Beyond authorship attribution: Can stylometry reveal the collective identity of literary texts and the gender of their authors? A comparative study of narrative fiction from Europe and Africa

Publikacja: 16.12.2025

Status artykułu: Otwarte __T_UNLOCK

Licencja: CC BY 4.0  ikona licencji

Udział procentowy autorów:

Adam Pawłowski (Autor) - 33.33%
Ewa Kalinowska (Autor) - 33.33%
Tomasz Walkowiak (Autor) - 33.33%

Informacje o autorze:

Adam Pawłowski graduated from the Wrocław University of Technology (Computer Science and Management) and the University of Wrocław (Romance Philology). He obtained his academic degrees from the University of Lausanne (1996) and the University of Warsaw (2002), and became a full professor in 2012. His research interests include digital humanities, quantitative linguistics, and contemporary language policy. A restless spirit, he seeks the unity and universality of knowledge, building bridges between the humanities and the world of numbers – often in opposition to the fragmented nature of institutionalized science. He is the author or co-author of over a hundred scholarly articles and several monographs. He also actively collaborates with the CLARIN-PL (language technology) and DARIAH-PL (digital humanities) research consortia. Prof. Pawłowski has been affiliated with the University of Wrocław since the beginning of his academic career.

Ewa Kalinowska is Associate Professor at the Institute of Applied Linguistics of the University of Warsaw. Her research focuses on French-language literatures from sub- Saharan Africa and the Indian Ocean islands. She has published sevral articles and two monographs devoted to various aspects of African literatures: Diseurs de vérité. Conceptions et enjeux de l’écriture engagée dans le roman africain de langue française [Truth-Tellers: Conceptions and Challenges of Engaged Writing in the French- Language African Novel] (Lublin 2018), and DOOLE JIGÉEN. Littérature des auteures d’expression française au Sénégal [DOOLE JIGÉEN. Literature of French-Speaking Women Authors in Senegal] (Warszawa 2025). She is the author of several articles (https://uw.academia.edu/EwaKalinowska). Member of the Association of Polish Africanists (Polskie Towarzystwo Afrykanistyczne) and Association pour l’Étude des Littératures Africaines (APELA).

Tomasz Walkowiak, PhD, Eng. is an Assistant Professor at the Department of Artificial Intelligence, Faculty of Computer Science and Telecommunications, Wrocław University of Science and Technology, Poland. His research interests include natural language processing, text and image analysis, distributed systems, and cloud computing. He contributes to the development and deployment of PLLuM, a large Polish language model, and conducts research in outlier detection, open-set classification, and Trustworthy and Robust AI. A key member of the CLARIN-PL project, he received the Steven Krauwer Award (2020) for outstanding achievements in language technology. He has co-authored numerous publications on NLP, stylometry, performance analysis, and adversarial robustness of AI models.

Korekty artykułu:

-

Języki publikacji:

Francuski

Au-delà de l’attribution d’auteur : la stylométrie permet-elle d’identifier l’« identité collective » des textes littéraires et le sexe des auteurs ? Analyse comparée de la fiction narrative d’Europe et d’Afrique

cytuj

Pobierz PDF Pobierz

pobierz pliki

RIS BIB ENDNOTE