Poetry Machines Empowering Creative Writers to Design DH Tools

1. Abstract

Digital Humanists often build tools based on their own understanding of what features users will need, whether intuited or derived from user studies. In the spirit of a key theme of DH2020---Public Digital Humanities---our presentation will consider what happens when we as researchers instead empower people to design their own DH tools according to their (perhaps idiosyncratic) purposes.

With our project, "Poetry Machines," we are recruiting individual poets who are not themselves programmers or machine learning practitioners to design their own artificially intelligent tools that will assist or challenge them in the middle of the writing process.

This research takes the approach of "participatory design" (Muller and Kuhn 1993). We have composed a design guide, a "boundary object" (Star and Griesemer 1989) providing a way for the poets to design their own poetry machines by combining various basic text processing functions and machine learning techniques into complex interfaces. We will then build these interfaces to their specifications, working with them collaboratively to further refine and develop designs (for instance, by presenting options of how a particular wished-for feature could be implemented).

A few possible functions that such machines could perform (the first two drawing from our own research [Booten 2019; Gero and Chilton 2019]):
•   provide stylistic advice, e.g. alert the writer when she has used highly common lexico-semantic patterns or descriptors (e.g. 'glowing' to describe 'moon')
•   replace a word with a synonym that is characteristic of a particular author
•   whenever the writer pauses for too long, complete the line with a neural network

Our design guide provides the poet with substantial flexibility in terms of how the Poetry Machine is activated (for instance, randomly vs. after every line), how it intervenes (for instance, adding to the poem or displaying information in a sidebar), and how machine learning models are trained (for instance, a neural network trained on Romantic vs. modernist poetry).

Our research goals are to determine: 1) whether different sorts of poets (e.g. formalists vs. more experimental writers) make different design choices, 2) whether the machines meet their design expectations, and 3) whether this process provides the poets opportunity to develop critical perspectives on machine learning itself. Having acquired institutional approval to solicit poets for formal research, we are in the process of engaging poets in the participatory design process, and our presentation will offer preliminary findings.

This work intervenes in several DH fields:
•   Though we are inspired by key examples of aesthetically-experimental hermeneutic interfaces (e.g. Clement 2008; McCurdy et al. 2016), our research will be of interest to DH tool designers more broadly, especially those interested in "bespoke" tools (Lin 2012).
•   "Electronic literature" is part of DH (Rettberg 2015; see also Berkman 2017). Programmer-poets often design their own tools for algorithmic co-writing (e.g. Johnston's [2019] neural-network assisted ReRites). Our project aims to make this "e-lit" practice more widely available.
•   This research connects to conversations about using DH to expand algorithmic literacy (D'Ignazio and Bhargava 2018).


Berkman, Natalie. "Digital Oulipo: Programming Potential Literature." DHQ: Digital Humanities Quarterly, vol. 11, no. 1, 2017. http://www.digitalhumanities.org/dhq/vol/11/3/000325/000325.html

Booten, Kyle. "Toward Digital Progymnasmata." Proceedings of the 10th International Conference on Computational Creativity, edited by Kazjon Grace, Michael Cook, Dan Ventura, and Mary Lou Maher, Association for Computational Creativity, 2019.

Clement, Tanya E. "‘A Thing Not Beginning and Not Ending’: Using Digital Tools to Distant-Read Gertrude Stein's The Making of Americans." Literary and Linguistic Computing, vol. 23, no. 3, 2008, pp. 361-381.

D'Ignazio, Catherine, and Rahul Bhargava. "Creative Data Literacy: A Constructionist Approach to Teaching Information Visualization." DHQ: Digital Humanities Quarterly, vol. 12, no. 4, 2018. http://digitalhumanities.org/dhq/vol/12/4/000403/000403.html

Gero, Katy Ilonka, and Lydia B. Chilton. "How a Stylistic, Machine-Generated Thesaurus Impacts a Writer's Process." Proceedings of the 2019 Conference on Creativity and Cognition, edited by Steven Dow, Mary Lou Maher, Andruid Kerne, and Celine Latulipe, Association for Computing Machinery, 2019.

Johnston, David Jhave. ReRites. Montreal, Anteism, 2019.

Lin, Yu-wei. "Transdisciplinarity and Digital Humanities: Lessons Learned from Developing Text-Mining Tools for Textual Analysis." Understanding Digital Humanities, edited by David M. Berry, Palgrave Macmillan, London, 2012, pp. 295-314.

McCurdy, Nina, et al. "Poemage: Visualizing the Sonic Topology of a Poem." IEEE Transactions on Visualization and Computer Graphics, vol. 22, no. 1, 2015, pp. 439-448.

Muller, Michael J., and Sarah Kuhn. "Participatory Design." Communications of the ACM, vol. 36, no. 6, 1993, pp. 24-28.

Rettberg, Scott. "Electronic Literature as Digital Humanities." A New Companion to Digital Humanities, edited by Susan Schreibman, Ray Siemens, and John Unsworth, Wiley, 2015, pp. 127-136.

Star, Susan Leigh, and James R. Griesemer. "Institutional Ecology, Translations' and Boundary Objects: Amateurs and Professionals in Berkeley's Museum of Vertebrate Zoology, 1907-39." Social Studies of Science, vol. 19, no. 3, 1989, pp. 387-420.

Kyle Paul Booten (kyle.p.booten@dartmouth.edu), Dartmouth College, United States of America and Katy Ilonka Gero (katy@cs.columbia.edu), Columbia University, United States of America

Theme: Lux by Bootswatch.