Info: The Journal of Cultural Analytics is hiring two grad positions!

Seeking a Copy-Editor and Editorial Assistant role. Apply here.

Rebecca Sutton Koeser

Lead Research Software Engineer

Ph.D. English Literature, Emory University

B.A., English Literature and Math/Computer Science, Wheaton College (IL)

network analysis
data visualization
english
Digital Humanities
Data Development
3D Modeling
Digital Research Infrastructures
database
Agent-based Modeling
Multilingual
Information Retrieval
Rebecca Sutton Koeser

As CDH Lead Research Software Engineer, Rebecca Sutton Koeser co-leads the CDH Research Software Engineering Team with Assistant Director Jeri Wieringa and partners with faculty to create custom research software through CDH collaborative projects. Recent collaboration outputs include data essays on Princeton Geniza Project datasets with Marina Rustow and Shakespeare and Company Project v2 dataset with Joshua Kotin, both published in the Journal of Cultural Analytics; a dataset of poetry excerpts mined from Princeton Prosody Archive; an article on the HTR2HPC pilot with Christine Roughan presented at USRSE25; and a short paper on unstable data in Princeton Prosody Archive with Meredith Martin and Mary Naydan, presented at Computational Humanities Research 2025.

Rebecca has training in both English Literature and Computer Science, combined with two decades of experience of software engineering in an academic environment. Her wide-ranging interests enable deep engagement in partnerships with faculty from a range of disciplines which have included English Literature, History and Near Eastern Studies, and Philosophy. Current research interests include computing with missing and partial data, as reflected in the article "Missing Data, Speculative Reading", co-authored with Zoe LeBlanc, and the python library undate for working with partially known and fuzzy dates, which expands on work from the Shakespeare and Company Project and the Princeton Geniza Project. She has expertise and interest in data visualization and data physicalization, and helping shape and improve research software development practices and Research Software Engineering for the humanities.

Rebecca serves on the DHTech (ADHO Special Interest Group) Steering Committee, where she is involved in Code Review Working Group and DH Community Code Review efforts; she co-edited with Julia Damerow the Digital Humanities Tech Symposium 2025 proceedings, which were published in the Anthology of Computers and Humanities. She is an associate editor for the Computational Humanities Research journal, where she has been working to establish the Software Paper as a genre for the field and is currently co-editing a themed issue on reproducibility with Miguel Escobar Varela. She previously served on the Association for Computers and the Humanities (ACH) Executive Council (2019-2023).

Highlighted articles

Princeton Geniza Project datasets

With Marina Rustow, published in Journal of Cultural Analytics. Documents 40-year PGP history, data modeling choices, dataset potential. (2026)

20260609_marina_pointing_pgp

Shakespeare and Company Project Data Sets, Version 2.0

With Joshua Kotin, published in Journal of Cultural Analytics. Research and potential of v2 dataset, including addresses. (2026)

jca-1114_kotin-g6

Undate: humanistic dates for computation

A software paper about the background, development, and potential of the undate python library. (2025)

Undate logo reading undate in blue and green gradient text, centered on a background of blue, teal, and light green color blocks arranged in a grid.

Missing Data, Speculative Reading

Estimating, analyzing, and speculating about gaps in Shakespeare and Company Project data; co-authored with Zoe LeBlanc (2024)

hemingway-missing

Data Beyond Vision

Experiments with data physicalization and DH data, published in the first issue of Startwords (2020)

data-beyond-vision-card.jpg

Trusting Others to 'Do the Math'

Who are we trusting when we use software for research? (2015)

rsk_trustingothers_belfastnetwork

Related projects

undate

An ambitious in-progress effort to develop a pragmatic Python package for the computation and analysis of temporal information.
Undate logo reading undate in blue and green gradient text, centered on a background of blue, teal, and light green color blocks arranged in a grid.

MuSE (Multilingual Semantic Embeddings)

Linking concepts in music-theoretical texts across languages

Built by CDH
music

remarx

A text-reuse detection tool built on semantic embeddings, remarx enables scholars to surface and connect related texts across documents, regardless of language.

Built by CDH
marx

Related events

Poster Session II at DH2024

Aug 9 2024 2:00PM–3:30PM
Rebecca Sutton Koeser
Meredith Martin
Mary Naydan
DH2024
ppa

Poster Session I at DH2024

Aug 7 2024 6:00PM–7:30PM
Lara Buchak
Wouter Haverals
Ryan Heuser
Rebecca Sutton Koeser
Zoe LeBlanc
Meredith Martin
Jeri Wieringa
DH2024
folding-installation-photo

DH Inside Out: Mini-Conference at DH2024

Aug 5 2024 9:00AM–4:30PM
Rebecca Sutton Koeser
DH2024
simrisk-hawkdove-agents

Related posts

Read-Only: A New Phase for Derrida's Margins

13 January 2025

Jeri Wieringa, Rebecca Sutton Koeser

CDH Project
Website page titled “interventions” with overlapping images of annotated texts, large orange heading text, and filter controls for author, ink type, and publication year.