Is Luke the author of a Gospel and the Acts of the Apostles?
Open accessThe DOI matches its Crossref record; 38 of the 61 references it cites were found in a registry or an index, and 13 are not checked yet; none of the 21 sources its claims cite is checked for support yet.
Abstract
According to Christian tradition, Luke is credited with authoring a Gospel and the Acts of the Apostles, even if his name does not appear in either book, both originally written in Koine Greek. Several biblical scholars assume that both texts were written by a common author, while others deduce the presence of two authors. Different studies have been found to support either finding, some based on qualitative evaluation, while a few others consider the occurrence frequency differences between the two books. To propose an enhanced quantitative analysis, this study is grounded on two recent authorship attribution models. The Burrows’ Delta, applied with eleven different feature sizes, demonstrates common authorship. An author verification model confirms this finding. The following experiments consider several stylistic representations, feature sizes, and distance functions to confirm that Luke is the true author of both books.
Checked 2026-10-05 · 13 references not checked yet
Overview
CoChat Summary
## TL;DR
The paper applies stylometric authorship attribution and verification methods to Luke and Acts in Koine Greek and argues that they have a common author. Across its tests, Burrows’ Delta and a verification model both consistently support Luke as the author of both books.
## Key findings
- Burrows’ Delta was run with 11 feature-set sizes and “always indicates common authorship” for Luke’s Gospel and Acts.
- In the verification experiments, the model was run with 8 stylistic representations, 6 similarity/distance measures, 10 feature sizes, and 1,000 iterations per feature size; it “always confirms” common authorship.
- The corpus used for the main comparison included Luke (19,482 tokens) and Acts (18,450 tokens); the paper also reports that the two books together are about 28% of the New Testament.
- The paper reports that reliable assessment generally required 100 or more features; with fewer than 200 features in the verification table, results were said to need caution.
## Methods
- Design: Quantitative authorship attribution/verification study comparing Luke and Acts against other New Testament books and impostor texts.
- Data/sample: Koine Greek texts downloaded from Bibelwissenschaft.de; the main corpus included the Gospels of Matthew, Mark, Luke, John, Acts, four Pauline letters, and Revelation, with chapter/token counts listed in Table 1. The verification model chunked Luke and Acts into 5,000-token segments.
- Main analysis: The study used Burrows’ Delta with multiple feature sizes, then an authorship verification model (Koppel & Seidman, 2018) with multiple stylistic representations (MFW, n-grams, truncation words), several distance/similarity measures (including cosine, MinMax, Dice, Manhattan, Tanimoto, Euclidean), and random selection of 50% of features over 1,000 iterations.
## Limitations
- The paper explicitly says this study “must be viewed as a first step” and that applying modern statistical modeling to Christian literature is “a largely open domain.”
- The author notes that the number of texts used is limited, so the probability estimates “must [be taken] with a grain of salt.”
- The text makes evident that the study depends on specific corpus choices and preprocessing (e.g., chapter-based Greek texts, verse-number/title removal, and a limited set of impostor texts), which may constrain generalization.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 2 Not valid · 14 Not checked · 48 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For example, the word Παῦλος (Paul, noun, masc. sing. nom.) appears 55 times in Luke's writings, but only 9 occurrences appear with the other writers.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other circumstances, such as the last portion of Acts (Paul travelling at sea), the system found some similarity with the beginning of John's Gospel.”
hedgedstates an associationSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For example, when applying the cosine similarity with 50, 75, 100, and 150 features, the result vector has a first component that is lower than 0.8 (the d threshold).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Third, a topical relationship clearly appears between the contents of both books in their justification of preaching not to the Jews, but to the Gentiles”
What the sources say
- Not checked — no full text of the sourcecites Burkett 2019 source
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Applying this variant, the Z score associated to Παῦλος (Paul) is now 7.37.”
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
22 more claims
Create a free account to see all 64 claims and every source verdict.
- Probably not a substantial claim. 20
- It may state two separate claims as one. 21
- The quote only partly states this claim. 2
Citations
Cites
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Introduction to Information Retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · doi:10.1017/cbo9780511809071 · Cited by 11,288
Machine learning in automated text categorization
Sebastiani, F. (2002) · ACM Computing Surveys · doi:10.1145/505282.505283 · Cited by 7,926
Analyzing Linguistic Data: A Practical Introduction to Statistics using R
Baayen, R. H. (2008) · doi:10.1017/cbo9780511801686 · Cited by 3,253
An Introduction to Statistical Learning: with Applications in R
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021) · Springer Texts in Statistics · doi:10.1007/978-1-0716-1418-1 · Cited by 1,755
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
Zheng, R., Li, J., Chen, H., & Huang, Z. (2006) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.20316 · Cited by 519
Shakespeare, Computers, and the Mystery of Authorship
(2009) · Cambridge University Press eBooks · doi:10.1017/cbo9780511605437 · Cited by 284
Attributing Authorship: An Introduction
Love, H. (2002) · doi:10.1017/cbo9780511483165 · Cited by 235
Determining if two documents are written by the same author
Koppel, M., & Winter, Y. (2014) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.22954 · Cited by 227
Does Size Matter? Authorship Attribution, Small Samples, Big Problem
Eder, M. (2015) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqt066 · Cited by 214
Grant, R. M., & Robinson, J. A. T. (1978) · Journal of Biblical Literature · doi:10.2307/3265647 · Cited by 199
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 application of principal component analysis to stylometry
Binongo, J., & Smith, M. (1999) · Literary and Linguistic Computing · doi:10.1093/llc/14.4.445 · Cited by 136
Measuring Differentiability: Unmasking Pseudonymous Authors
KoppelMoshe, SchlerJonathan, & Bonchek-DokowElisheva (2007) · Journal of Machine Learning Research · doi:10.5555/1314498.1314541 · Cited by 102
Authorship Determination Using Letter Pair Frequency Features with Neural Network Classifiers
Kjell, B. P. (1995) · Literary and Linguistic Computing · doi:10.1093/llc/9.2.119 · Cited by 100
Rethinking the Unity of Luke and Acts
Parsons, M. C., & Pervo, R. I. (1993) · doi:10.2307/j.ctv1hqdhds · Cited by 96
Experiments on authorship attribution by intertextual distance in english*
Labbé, D. (2007) · Journal of Quantitative Linguistics · doi:10.1080/09296170600850601 · Cited by 86
Hoover, D. L. (2004) · Literary and Linguistic Computing · doi:10.1093/llc/19.4.477 · Cited by 86
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
Machine Learning Methods for Stylometry: Authorship Attribution and Author Profiling
Savoy, J. (2020) · doi:10.1007/978-3-030-53360-1 · Cited by 67
Self-citationDistance measures in author profiling
Kocher, M., & Savoy, J. (2017) · Information Processing & Management · doi:10.1016/j.ipm.2017.04.004 · Cited by 66
Self-citationOverview of the PAN/CLEF 2015 Evaluation Lab
Stamatatos, E., Potthast, M., Rangel, F., Rosso, P., & Stein, B. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-24027-5_49 · Cited by 57
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
The Synoptic Problem: A Way Through the Maze
Goodacre, M. (2001) · doi:10.5040/9780567691187 · Cited by 44
Goodacre, M. (2001) · SBL Press eBooks · doi:10.15699/9781589836327-010 · Cited by 44
Gender identification on Twitter
Ikae, C., & Savoy, J. (2021) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.24541 · Cited by 39
Self-citationDetecting pseudepigraphic texts using novel similarity measures
Koppel, M., & Seidman, S. (2017) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqx011 · Cited by 34
Is Starnone Really the Author Behind Ferrante?
Savoy, J. (2018) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqy016 · Cited by 32
Self-citationEvaluation of text representation schemes and distance measures for authorship linking
Kocher, M., & Savoy, J. (2018) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqy013 · Cited by 31
Self-citationAuthorship of Pauline Epistles Revisited
Savoy, J. (2019) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.24176 · Cited by 26
Self-citationEntropy-Based Authorship Search in Large Document Collections
Zhao, Y., & Zobel, J. (2007) · Springer eBooks · doi:10.1007/978-3-540-71496-5_35 · Cited by 21
An Introduction to the New Testament and the Origins of Christianity
Burkett, D. (2019) · doi:10.1017/9781316779361 · Cited by 19
The Literary Unity of Luke-Acts: Questions of Style – a Task for Literary Critics
Dawsey, J. (1989) · New Testament Studies · doi:10.1017/s0028688500024498 · Cited by 19
An Introduction to the New Testament and the Origins of Christianity
Burkett, D. (2002) · doi:10.1017/cbo9780511801457 · Cited by 18
THE PROBLEM OF ANONYMITY AND PSEUDONYMITY IN CHRISTIAN LITERATURE OF THE FIRST TWO CENTURIES1
Aland, K. (1961) · The Journal of Theological Studies · doi:10.1093/jts/xii.1.39 · Cited by 15
The Assumed Authorial Unity of Luke and Acts
WALTERS, P. A. (2009) · Cambridge University Press eBooks · doi:10.1017/cbo9780511575204 · Cited by 12
Argyle, A. W. (1974) · New Testament Studies · doi:10.1017/s0028688500012261 · Cited by 7
The Common Authorship of Luke and Acts
Beck, B. E. (1977) · New Testament Studies · doi:10.1017/s0028688500010602 · Cited by 7
The Seams and Summaries of Luke and of Acts
Mealand, D. L. (2016) · Journal for the Study of the New Testament · doi:10.1177/0142064x16637779 · Cited by 4
Mathematically Modeling Early Christian Literature: Theories, Methods, and Future Directions
Pracht, E. B. (2025) · Open Theology · doi:10.1515/opth-2025-0061 · Cited by 1
French Literature in Polish: A Quantitative Reconnaissance
Rybicki, J. (2025) · Romanica Cracoviensia · doi:10.4467/20843917rc.25.041.22754 · Cited by 1
Paulus, Der Apostel Jesu Christi, Sein Leben Und Wirken, Seine Briefe Und Seine Lehre
Baur (1845)
UnresolvedLa Vie Des Évangiles. Initiation à la Critique Des Textes
Boismard (1980)
UnresolvedLe Texte Occidental Des Actes Des Apôtres. Reconstitution et Réhabilitation
Boismard (1984)
UnresolvedRethinking the Unity and Reception of Luke and Acts
Bovon (2010)
UnresolvedThe Making of Luke-Acts
Cadbury (1927)
UnresolvedAn Introduction to the New Testament
Carson (2005)
UnresolvedThe Acts of the Apostles
Clark (1933)
UnresolvedRethinking the Unity and Reception of Luke and Acts
Gregory (2010)
UnresolvedActs: A Commentary
Holladay (2016)
UnresolvedUntitled work
Kešelj (2003)
UnresolvedLinguistic Fingerprints. How Language Creates and Reveals Identity
Kreuz (2023)
UnresolvedNote on the General Case of the Bayes-Laplace Formula for Inductive or A Posteriori Probabilities
Lidstone (1920) · Transactions of the Faculty of Actuaries
UnresolvedFoundations of Statistical Natural Language Processing
Manning (2001)
UnresolvedPrincipes et Méthodes de Statistique Lexicale
Muller (1992)
UnresolvedDating Acts: Between the Evangelists and the Apologists
Pervo (2006)
UnresolvedRethinking the Unity and Reception of Luke and Acts
Pervo (2010)
UnresolvedExperimental IR Meets Multilinguality, Multimodality, and Interaction. Proceedings 6th International Conference of the CLEF Initiative (CLEF 15)
Stamatatos (2015)
UnresolvedWhen and Why Was the Acts of Apostles Written?
Tyson (2011)
UnresolvedProceedings ECIR
Zhao (2007)
Unresolved
Metadata
- Authors
- Savoy, J.
- Affiliations
- University of Neuchâtel (CH)
- Corresponding author
- Savoy, Jacques
- ORCID
- Savoy, Jacques
- Venue
- Digital Scholarship in the Humanities
- Publisher
- Oxford University Press (OUP)
- Published
- 2026-09-21
- ISSN
- 2055-7671 (ISSN-L)
- 2055-768X
- OpenAlex
- W7213529827
- Cited by
- 0
- References
- 56
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Digital Scholarship in the Humanities (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- 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 › Arts and Humanities › Religious studies › Biblical Studies and Interpretation
- Keywords
- Gospel of Luke, Acts of the Apostles, authorship attribution, Burrows' Delta, author verification, stylistic features, Koine Greek, New Testament, quantitative stylistics
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.
A language model drew the claims from the paper on 2026-10-01, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-01 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.