Pramit Chaudhuri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Pramit Chaudhuri has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Joseph P. Dexter
Data Science Initiative, Harvard University, Allston, MA, United States
9 shared publications - Thomas J. Bolt3 shared publications
- Aleksandr Fedchin
Tufts University, Medford, USA
2 shared publications - Isabel Cooperman
Department of Classical and Ancient Near Eastern Studies University of Wisconsin-Madison
2 shared publications - Madison Ski Krieger
Harvard University
2 shared publications Tathagata Dasgupta
Department of Systems Biology, Harvard Medical School, MA, USA
2 shared publications
Latest Publications
- 22 October 2025
- Published by Taylor & Francis
- p. 114-134
Stylometry for Latin Literary Criticism
This chapter provides a brief overview of methods for quantitative analysis of writing style (“stylometry”) with Latin texts. Stylometry is most commonly applied to questions of authorship, dating, and textual emendation – areas traditionally associated with classical philology. Here, we take a different approach by exploring how stylometric evidence can inform Latin literary criticism, a newer and increasingly important direction within the field. The chapter is especially intended for humanists put off by computational work because of the challenges of acquiring technical skills in programming and statistics. Emphasis of the latter can obscure the fundamental role played by linguistic and literary training not only in driving an overall research agenda but also in specifying the details of experimental design. We begin, therefore, by showing how formal linguistic and literary features routinely studied by humanists can be deployed in ways amenable to computational analysis and in the service of answering questions of scholarly interest. Through a series of case studies, we describe work, by our group and others, on the development of feature sets to capture salient aspects of the Latin literary style. We then outline how those features can be used in computational pipelines to identify stylistic similarities and differences across a range of scales, from individual works to entire genres and traditions. In the course of this discussion, we provide a brief but self-contained introduction to key concepts of machine learning, including supervision, training, cross-validation, and interpretability.
- 22 October 2025
- Published by Taylor & Francis
- p. 114-134
Stylometry for Latin Literary Criticism
This chapter provides a brief overview of methods for quantitative analysis of writing style (“stylometry”) with Latin texts. Stylometry is most commonly applied to questions of authorship, dating, and textual emendation – areas traditionally associated with classical philology. Here, we take a different approach by exploring how stylometric evidence can inform Latin literary criticism, a newer and increasingly important direction within the field. The chapter is especially intended for humanists put off by computational work because of the challenges of acquiring technical skills in programming and statistics. Emphasis of the latter can obscure the fundamental role played by linguistic and literary training not only in driving an overall research agenda but also in specifying the details of experimental design. We begin, therefore, by showing how formal linguistic and literary features routinely studied by humanists can be deployed in ways amenable to computational analysis and in the service of answering questions of scholarly interest. Through a series of case studies, we describe work, by our group and others, on the development of feature sets to capture salient aspects of the Latin literary style. We then outline how those features can be used in computational pipelines to identify stylistic similarities and differences across a range of scales, from individual works to entire genres and traditions. In the course of this discussion, we provide a brief but self-contained introduction to key concepts of machine learning, including supervision, training, cross-validation, and interpretability.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7430-7437
AcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora
Aleksandr Fedchin, Isabel Cooperman, Pramit Chaudhuri, Joseph P. Dexter. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7430-7437
Open AccessAcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora
Aleksandr Fedchin, Isabel Cooperman, Pramit Chaudhuri, Joseph P. Dexter. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- Open Access
AcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora
For centuries, writers have hidden messages in their texts as acrostics, where initial letters of consecutive lines or paragraphs form meaningful words or phrases. Scholars searching for acrostics manually can only focus on a few authors at a time and often favor qualitative arguments in discussing intentionally. We aim to put the study of acrostics on firmer statistical footing by presenting AcrosticSleuth, a first-of-its-kind tool that automatically identifies acrostics and ranks them by the probability that the sequence of characters does not occur by chance (and therefore may have been inserted intentionally). Acrostics are rare, so we formalize the problem as a binary classification task in the presence of extreme class imbalance. To evaluate AcrosticSleuth, we present the Acrostic Identification Dataset (AcrostID), a collection of acrostics from the WikiSource online database. Despite the class imbalance, AcrosticSleuth achieves F1 scores of 0.39, 0.59, and 0.66 on French, English, and Russian subdomains of WikiSource, respectively. We further demonstrate that AcrosticSleuth can identify previously unknown high-profile instances of wordplay, such as the acrostic spelling ARSPOETICA (``art of poetry") by Italian Humanist Albertino Mussato and English philosopher Thomas Hobbes' signature in the opening paragraphs of The Elements of Law.
Open AccessAcrosticSleuth: Probabilistic Identification and Ranking of Acrostics in Multilingual Corpora
For centuries, writers have hidden messages in their texts as acrostics, where initial letters of consecutive lines or paragraphs form meaningful words or phrases. Scholars searching for acrostics manually can only focus on a few authors at a time and often favor qualitative arguments in discussing intentionally. We aim to put the study of acrostics on firmer statistical footing by presenting AcrosticSleuth, a first-of-its-kind tool that automatically identifies acrostics and ranks them by the probability that the sequence of characters does not occur by chance (and therefore may have been inserted intentionally). Acrostics are rare, so we formalize the problem as a binary classification task in the presence of extreme class imbalance. To evaluate AcrosticSleuth, we present the Acrostic Identification Dataset (AcrostID), a collection of acrostics from the WikiSource online database. Despite the class imbalance, AcrosticSleuth achieves F1 scores of 0.39, 0.59, and 0.66 on French, English, and Russian subdomains of WikiSource, respectively. We further demonstrate that AcrosticSleuth can identify previously unknown high-profile instances of wordplay, such as the acrostic spelling ARSPOETICA (``art of poetry") by Italian Humanist Albertino Mussato and English philosopher Thomas Hobbes' signature in the opening paragraphs of The Elements of Law.
- 1 January 2022
- Published by University of Chicago Press in Classical Philology
- Vol. 117 (1) , 200-209
More Latian Anagrams (Aen. 8.314–36)
This note offers a new reading of Evander’s speech at Aeneid 8.314–36. The passage contains a celebrated anagrammatic wordplay centering on the word Latium, to which we add several newly identified anagrams. We argue that these wordplays represent in microcosm the composition, disintegration, and recomposition of states leading up to and including Rome itself. In doing so, the anagrams convey an underlying evolutionary process in which elements—whether letters or peoples—are grouped differently over time to create new words and identities. At the same time, couched in Evander’s moralizing discourse about human evolution, the wordplay does more than merely exemplify societal change: formal features embody real-world processes with major historical and ethical effects.
- 1 January 2022
- Published by University of Chicago Press in Classical Philology
- Vol. 117 (1) , 200-209
More Latian Anagrams (Aen. 8.314–36)
This note offers a new reading of Evander’s speech at Aeneid 8.314–36. The passage contains a celebrated anagrammatic wordplay centering on the word Latium, to which we add several newly identified anagrams. We argue that these wordplays represent in microcosm the composition, disintegration, and recomposition of states leading up to and including Rome itself. In doing so, the anagrams convey an underlying evolutionary process in which elements—whether letters or peoples—are grouped differently over time to create new words and identities. At the same time, couched in Evander’s moralizing discourse about human evolution, the wordplay does more than merely exemplify societal change: formal features embody real-world processes with major historical and ethical effects.
- 11 November 2021
- Published by Springer Nature in Nature Human Behaviour
- Vol. 5 (11) , 1484-1486
Reply to: Beowulf single-authorship claim is unsupported
- 11 November 2021
- Published by Springer Nature in Nature Human Behaviour
- Vol. 5 (11) , 1484-1486
Reply to: Beowulf single-authorship claim is unsupported
- Top Cited Papers
- 8 April 2019
- Published by Springer Nature in Nature Human Behaviour
- Vol. 3 (6) , 560-567
Large-scale quantitative profiling of the Old English verse tradition
- 8 April 2019
- Published by Springer Nature in Nature Human Behaviour
- Vol. 3 (6) , 560-567
Top Cited PapersLarge-scale quantitative profiling of the Old English verse tradition
- 1 December 2018
- Published by Oxford University Press (OUP) in Digital Scholarship in the Humanities
- Vol. 34 (4) , 716-729
A small set of stylometric features differentiates Latin prose and verse
Identifying the stylistic signatures characteristic of different genres is of central importance to literary theory and criticism. In this article we report a large-scale computational analysis of Latin prose and verse using a combination of quantitative stylistics and supervised machine learning. We train a set of classifiers to differentiate prose and poetry with high accuracy (>97%) based on a set of twenty-six text-based, primarily syntactic features and rank the relative importance of these features to identify a low-dimensional set still sufficient to achieve excellent classifier performance. This analysis demonstrates that Latin prose and verse can be classified effectively using just three top features. From examination of the highly ranked features, we observe that measures of the hypotactic style favored in Latin prose (i.e. subordinating constructions in complex sentences, such as relative clauses) are especially useful for classification.
- 1 December 2018
- Published by Oxford University Press (OUP) in Digital Scholarship in the Humanities
- Vol. 34 (4) , 716-729
A small set of stylometric features differentiates Latin prose and verse
Identifying the stylistic signatures characteristic of different genres is of central importance to literary theory and criticism. In this article we report a large-scale computational analysis of Latin prose and verse using a combination of quantitative stylistics and supervised machine learning. We train a set of classifiers to differentiate prose and poetry with high accuracy (>97%) based on a set of twenty-six text-based, primarily syntactic features and rank the relative importance of these features to identify a low-dimensional set still sufficient to achieve excellent classifier performance. This analysis demonstrates that Latin prose and verse can be classified effectively using just three top features. From examination of the highly ranked features, we observe that measures of the hypotactic style favored in Latin prose (i.e. subordinating constructions in complex sentences, such as relative clauses) are especially useful for classification.
- Open Access
Bioinformatics and Classical Literary Study
This paper describes the Quantitative Criticism Lab, a collaborative initiative between classicists, quantitative biologists, and computer scientists to apply ideas and methods drawn from the sciences to the study of literature. A core goal of the project is the use of computational biology, natural language processing, and machine learning techniques to investigate authorial style, intertextuality, and related phenomena of literary significance. As a case study in our approach, here we review the use of sequence alignment, a common technique in genomics and computational linguistics, to detect intertextuality in Latin literature. Sequence alignment is distinguished by its ability to find inexact verbal similarities, which makes it ideal for identifying phonetic echoes in large corpora of Latin texts. Although especially suited to Latin, sequence alignment in principle can be extended to many other languages.
Open AccessBioinformatics and Classical Literary Study
This paper describes the Quantitative Criticism Lab, a collaborative initiative between classicists, quantitative biologists, and computer scientists to apply ideas and methods drawn from the sciences to the study of literature. A core goal of the project is the use of computational biology, natural language processing, and machine learning techniques to investigate authorial style, intertextuality, and related phenomena of literary significance. As a case study in our approach, here we review the use of sequence alignment, a common technique in genomics and computational linguistics, to detect intertextuality in Latin literature. Sequence alignment is distinguished by its ability to find inexact verbal similarities, which makes it ideal for identifying phonetic echoes in large corpora of Latin texts. Although especially suited to Latin, sequence alignment in principle can be extended to many other languages.
- 3 April 2017
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 114 (16) , E3195-E3204
Quantitative criticism of literary relationships
Significance: Famous works of literature can serve as cultural touchstones, inviting creative adaptations in subsequent writing. To understand a poem, play, or novel, critics often catalog and analyze these intertextual relationships. The study of such relationships is challenging because intertextuality can take many forms, from direct quotation to literary imitation. Here, we show that techniques from authorship attribution studies, including stylometry and machine learning, can shed light on inexact literary relationships involving little explicit text reuse. We trace the evolution of features not tied to individual words across diverse corpora and provide statistical evidence to support interpretive hypotheses of literary critical interest. The significance of this approach is the integration of quantitative and humanistic methods to address aspects of cultural evolution.
- 3 April 2017
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 114 (16) , E3195-E3204
Quantitative criticism of literary relationships
Significance: Famous works of literature can serve as cultural touchstones, inviting creative adaptations in subsequent writing. To understand a poem, play, or novel, critics often catalog and analyze these intertextual relationships. The study of such relationships is challenging because intertextuality can take many forms, from direct quotation to literary imitation. Here, we show that techniques from authorship attribution studies, including stylometry and machine learning, can shed light on inexact literary relationships involving little explicit text reuse. We trace the evolution of features not tied to individual words across diverse corpora and provide statistical evidence to support interpretive hypotheses of literary critical interest. The significance of this approach is the integration of quantitative and humanistic methods to address aspects of cultural evolution.