Computational Stylistics Group

Corpora

The following selection of links is but a tip of the iceberg when it comes to the corpora (text collections) suitable for text analysis. The corpora listed below, however, are compiled by the members of CSG, and checked for compatibility with commonly known stylometric software.

A Small Collection of British Fiction
100 Polish Novels
100 English Novels
68 German Novels
100 Russian Novels
Latin New Testament
Roman de la Rose, to play with the Rolling Classify method
ELTeC corpora - while our team prepared only the Polish corpus in the collection, we participated in all stages of collection design and strongly encourage you to check it out!

If you’re looking to test the methods on poetry or drama, we are also happy to recommend befriended projects:

PoeTree - “a standardized collection of poetry corpora comprising over 330,000 poems in ten languages (Czech, English, French, German, Hungarian, Italian, Portuguese, Russian, Slovenian, Spanish). Each corpus has been deduplicated, enriched with Universal Dependencies, provided with additional metadata and converted into a unified JSON structure.” PoeTree is a project headed by our colleagues from the Czech Academy of Sciences and is continuously growing.
DraCor - “(short for »drama corpora«) is an open digital infrastructure developed for the computational study of (mostly) European drama from Greco-Roman antiquity to the 20th century.” The project includes 21 and counting corpora of dramatic works with rich encoding facilitating analysis of various levels of drama. Like in the case of PoeTree, the corpora are continuously growing.

Documentation of the package ‘stylo’

for (real) beginners: a crash introduction in the form of a slideshow
for (sort of) beginners: a concise HOWTO
for advanced users: a paper in R Journal
full documentation at CRAN

Blog posts on non-obvious functions of the package ‘stylo’:

Method discussions:

CLS Infra Survey of Methods - an explorable grid of short papers introducing various aspects of stylometric studies in regard to some literary problems, i.a., corpus preparation, analysis and evaluation steps.
Multilingual stylometry showcases

Video introductions

Publications

A list of relevant publications by the CSG members can be found on this website, on the subpage ‘publications‘. However, a comprehensive Stylometry Bibliography, curated by Christof Schöch, is definitely a place to consult before starting any experiment in text analysis.

Learn with us

The members of the group regularly conduct invited workshops at various places of the world, including yearly course offerings at Digital Humanities Summer Institute (DHSI) in Victoria BC and The European Summer University in Digital Humanities (ESUDH) in Leipzig. Below we aim to list some upcoming events:

2025 major workshops

19-23 May Interdisciplinary Methodologies in Linguistic Research in Kraków, Poland. Lectures offered by Joanna Byszuk, Maciej Eder and Rafał L. Górski.
26-20 May Digital Humanities Summer Institute in Montreal, Canada. Week 1, taught by Joanna Byszuk and Jacek Bąkowski.
21 July - 2 August European Summer University in Digital Humanities “Culture & Technology” in Besançon, France. Course: Distant Reading in R. Analyse the text & visualize the data (Artjoms Šeļa, Czech Academy of Sciences, and Giovanni Pietro Vitali, University of Versailles Saint-Quentin-en-Yvelines)

2024 major workshops

15–26 July European Summer University in Digital Humanities “Culture & Technology” in Cluj-Napoca, Romania. Taught by Artjoms Šeļa and Jeremi Ochab.
10–14 June Digital Humanities Summer Institute in Victoria BC, Canada. Week 2, taught by Joanna Byszuk and Jeremi Ochab.
~~3–7 June Digital Humanities Summer Institute in Victoria BC, Canada. Week 1, taught by Maciej Eder~~.

2023 major workshops

4–8 Sept IQLA-GIAT Summer School in Quantitative Analysis of Textual Data in Padua, Italy. Taught by Joanna Byszuk.
5–9 June Digital Humanities Summer Institute in Victoria BC, Canada. Taught by Maciej Eder.
10–12 May CLS INFRA Training School in Madrid, at UNED. Taught by Joanna Byszuk and Artjoms Šeļa.

2022 major workshops

2–12 Aug European Summer University in Digital Humanities in Leipzig, Germany. Taught by Maciej Eder and Jeremi K. Ochab.
22–24 March COST Action Winter School in Belgrade. Taught (remotely) by Joanna Byszuk, Artjoms Šeļa and Maciej Eder.

2021 major workshops

3–13 Aug European Summer University in Digital Humanities in Leipzig, Germany. Taught (remotely) by Maciej Eder and Jeremi K. Ochab.
26–30 July IQLA-GIAT Summer School in Quantitative Analysis of Textual Data in Padua, Italy. Taught (remotely) by Maciej Eder.
14–18 July Digital Humanities Summer Institute in Victoria BC, Canada. Taught (remotely) by Joanna Byszuk, Artjoms Šeļa and Maciej Eder.

2020 major workshops

1–3 July Stylometry and Arabic Sources, in London, at Aga Khan University. Taught (remotely) by Maciej Eder.
~~28 Jul – 7 Aug European Summer University in Digital Humanities in Leipzig, Germany. Taught by Maciej Eder and Jeremi K. Ochab.~~ Postponed to 2021.
~~15–19 June DHSI Atlantic in Cork, Ireland. Taught by Jan Rybicki.~~ Cancelled.
~~8–12 June Digital Humanities Summer Institute in Victoria BC, Canada. Taught by Maciej Eder and Joanna Byszuk.~~ Postponed to 2021.

2019 major workshops

9–13 Sep IQLA-GIAT Summer School in Quantitative Analysis of Textual Data in Padua, Italy. Taught by Maciej Eder and Jan Rybicki.
23 Jul – 2 Aug The European Summer University in Digital Humanities in Leipzig, Germany. Taught by Maciej Eder and Jeremi K. Ochab.
10–14 June Digital Humanities Summer Institute in Victoria BC, Canada. Taught by Maciej Eder and Joanna Byszuk.
3–5 May Stylometry at DHI Beirut in Beirut, Lebanon. Taught by Jan Rybicki.
28 Feb – 1 Mar Style/Content – Literary Modeling in Stockholm, Sweden. Taught by Jan Rybicki.

Resources

Materials prepared by the Group. (More to be added soon...).