Rolling stylometry
The DOI matches its Crossref record; 19 of the 21 references it cites were found in a registry or an index.
Abstract
This article introduces a new stylometric method that combines supervised machine-learning classification with the idea of sequential analysis. Unlike standard procedures, aimed at assessing style differentiation between discrete text samples, the new method, supported with compact visualization, tries to look inside a text represented as a set of linearly sliced chunks, in order to test their stylistic consistency. Three flavors of the method have been introduced: (1) Rolling SVM, relying on the support vector machines (SVM) classifier, (2) Rolling NSC, based on the nearest shrunken centroids method, and (3) Rolling Delta, using the classic Burrowsian measure of similarity. The technique is primarily intended to assess mixed authorship; however, it can be also used as a magnifying glass to inspect works with unclear stylometric signal. To demonstrate its applicability, three different examples of collaborative work have been briefly discussed: (1) the 13th-century French allegorical poem Roman de la Rose , (2) a 15th-century translation of the Bible into Polish known as Queen Sophia’s Bible , and (3) The Inheritors , a novel collaboratively written by Joseph Conrad and Ford Madox Ford in 1901.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
A survey of modern authorship attribution methods
Stamatatos, E. (2009) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.21001 · Cited by 1,176
Delta: A Measure of Stylistic Difference and a Guide to Likely Authorship
Burrows, J. (2002) · Literary and Linguistic Computing · doi:10.1093/llc/17.3.267 · Cited by 627
Computational methods in authorship attribution
Koppel, M., Schler, J., & Argamon, S. (2009) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.20961 · Cited by 528
Bigrams of Syntactic Labels for Authorship Discrimination of Short Texts
Hirst, G., & Feiguina, O. (2007) · Literary and Linguistic Computing · doi:10.1093/llc/fqm023 · Cited by 227 · cited 2×
“Some elements of sequential analysis have been implicitly used in several attribution studies involving word n-grams, character ngrams, or POS n-grams as discriminative features (Stamatatos, 2009; Koppel et al., 2009; Eder, 2011; Hirst and Feiguina, 2007), since n-grams are in fact sequentially ordered series of nonra…”
MethodDoes Size Matter? Authorship Attribution, Small Samples, Big Problem
Eder, M. (2015) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqt066 · Cited by 214 · cited 1×
“It has been shown that minimal sample length for authorship attribution is roughly 5,000 words, depending on the language and the genre examined (Eder, 2013).”
BackgroundSelf-citationHoover, D. L. (2004) · Literary and Linguistic Computing · doi:10.1093/llc/19.4.453 · Cited by 200
A comparative study of machine learning methods for authorship attribution
Jockers, M. L., & Witten, D. M. (2010) · Literary and Linguistic Computing · doi:10.1093/llc/fqq001 · Cited by 188
The Advanced Theory of Language as Choice and Chance
Herdan, G. (1966) · Springer eBooks · doi:10.1007/978-3-642-88388-0 · Cited by 136
Style-markers in authorship attribution : a cross-language study of the authorial fingerprint
Eder, M. (2011) · Jagiellonian University Repository (Jagiellonian University) · Cited by 134
Self-citationMarkov, A. A. (2006) · Science in Context · doi:10.1017/s0269889706001074 · Cited by 121
Using Markov chains for identification of writers
Khmelev, D. (2001) · Literary and Linguistic Computing · doi:10.1093/llc/16.3.299 · Cited by 116
Collaborative authorship: Conrad, Ford and Rolling Delta
Rybicki, J., Hoover, D. L., & Kestemont, M. (2014) · Literary and Linguistic Computing · doi:10.1093/llc/fqu016 · Cited by 89
The stylistics and stylometry of collaborative translation: Woolf's Night and Day in Polish
Rybicki, J., & Heydel, M. (2013) · Literary and Linguistic Computing · doi:10.1093/llc/fqt027 · Cited by 83
Delta for Middle Dutch Author and Copyist Distinction in Walewein
van Dalen-Oskam, K., & van Zundert, J. (2007) · Literary and Linguistic Computing · doi:10.1093/llc/fqm012 · Cited by 61
The great mystery of the (almost) invisible translator
Rybicki, J. (2012) · Studies in corpus linguistics · doi:10.1075/scl.51.09ryb · Cited by 44
Never Say Always Again: Reflections on the Numbers Game
Burrows, J. (2010) · Open Book Publishers · doi:10.11647/obp.0008.01 · Cited by 12
Pawłowski, A. (1999) · Journal of Quantitative Linguistics · doi:10.1076/jqul.6.1.70.4140 · Cited by 12
Quantity or Stress? Sequential Analysis of Latin Prosody
Pawłowski, A., & Eder, M. (2001) · Journal of Quantitative Linguistics · doi:10.1076/jqul.8.1.81.4093 · Cited by 3
Self-citation
Research works printed but not linked: 7
- Burrows, 2002, The Englishing of Juvenal: computational stylistics and transtated texts, Style, 36, 677
- Eder M Kestemont M Rybicki J . In Digital Humanities 2013: Conference Abstracts. Lincoln, NE: University of Nebraska-Lincoln; 2013. Stylometry with R: a suite of tools; p. 487-9.
- Hoover D L . In Digital Humanities: Conference Abstracts. Stanford, CA: Stanford University; 2011. “The Tutor’s Story”: a case study of mixed authorship; p. 149-51.
- Kestemont M van Dalen-Oskam K . Predicting the past: memory-based copyist and author discrimination in medieval epics. In Proceedings of the 21st Benelux Conference of Artificial Intelligence (BNAIC) 2009. 2009. Eindhoven, pp. 121–8.
- Marteau P , editor. 1878. Le Roman de la rose, par Guillaume de Lorris et Jean de Meung. Éd. accompagnée d'une traduction en vers, précédée d’une introduction, notices historiques et critiques; suivie de notes et d'un glossaire par Pierre Marteau. Vol. 1–4. Orléans: H. Herluison.
- Tabata T . In Digital Humanities 2014: Conference Abstracts. Lausanne: EPFL–UNIL; 2014. Stylometry of collaborations: Dickens, Collins and their collaborative writings; p. 378-80.
- Urbańczyk, 1933, Jeden czy kilku tłumaczy Biblii szaroszpatackiej, Slavia Occidentalis, 13, 25
Cited by
What is Elena Ferrante? A comparative analysis of a secretive bestselling Italian writer
Tuzzi, A., & Cortelazzo, M. A. (2018) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqx066 · Cited by 46
“…Juola and Stamatatos, 2013; Rybicki et al. , 2016), e.g. stylometry and similarity measures (Holmes, 1998; Labbe´ and Labbe´, 2001; Burrows, 2002; Eder 2013, 2015, 2016; Ratinaud and Marchand, 2016), compression algorithms, entropic methods, and long-range correlations (Benedetto et al. ,…”
Plecháč, P. (2020) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqaa032 · Cited by 34
“Rolling attribution was originally introduced by Maciej Eder [32] as a technique designed for cases involving mixed authorship.”
MethodDeconstructing the Authorship of Siempre ayuda la verdad: A Play by Lope de Vega?
García‐Reidy, A. (2019) · Neophilologus · doi:10.1007/s11061-019-09607-8 · Cited by 31
McCarthy, R., & O’Sullivan, J. (2020) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqaa031 · Cited by 29
Versification and Authorship Attribution
Plecháč, P. (2021) · Karolinum Press eBooks · doi:10.14712/9788024648903 · Cited by 23
Metadata
- Authors
- Eder, M.
- Affiliations
- Uniwersytet Komisji Edukacji Narodowej w Krakowie (PL)
- Corresponding author
- Eder, Maciej
- ORCID
- Eder, Maciej
- Venue
- Digital Scholarship in the Humanities
- Publisher
- Oxford University Press (OUP)
- Published
- 2015-04-06
- Volume
- 31
- Issue
- 3
- Pages
- 457-469
- ISSN
- 2055-7671 (ISSN-L)
- 2055-768X
- OpenAlex
- W4255671361
- Cited by
- 68
- References
- 21
- Citations by year
- 2026: 8 · 2025: 15 · 2024: 5 · 2023: 5 · 2022: 4 · 2021: 7 · 2020: 16 · 2019: 2 · 2018: 3 · 2017: 2 · 2015: 1
- FWCI
- 1.96
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Digital Scholarship in the Humanities (publishedVersion)
- HighWire Press Open Archive (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Social Sciences › Arts and Humanities › Literature and Literary Theory › Digital Humanities and Scholarship
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Keywords
- authorship attribution, collaborative writing, stylistic consistency, support vector machine, nearest shrunken centroids, Roman de la Rose, The Inheritors, Joseph Conrad, Ford Madox Ford, Bible translation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.