No CrossRef data available.
We use cookies to distinguish you from other users and to provide you with a better experience on our websites. Close this message to accept cookies or find out how to manage your cookie settings.
We use cookies to distinguish you from other users and to provide you with a better experience on our websites. Close this message to accept cookies or find out how to manage your cookie settings.
Published online by Cambridge University Press: 21 July 2025
Chronology is an important framing mechanism in history and changes significantly based on who defines historical eras. The area studies field has recently grappled with the need to decenter perspectives and reconsider the sources that scholars use. This article uses deep learning artificial intelligence methods to process 169,634 images from the Russian State Documentary Film and Photo Archive (RGAKFD), a major archive of photography in the region, as containing a statist chronological logic, one defined by political change in the center. By peering under the hood of the algorithm’s predictions, by thinking with the machine, it is possible to see patterns in the images that may not seem crucial to the human eye. Looking at RGAKFD as a potential source of data for AI raises parallels between algorithmic bias and the Moscow-centric bias of sources, while also providing opportunities to use such methods as a tool for exploratory research.
I am thankful to Paula Chan, Nic Delorme, Andy Janco, Dan Maxwell, and Joan Neuberger for their careful readings of this article. In addition to reading the article as a draft, Joan Neuberger helped arrange one of the figures that appears in it. Dan Maxwell also organized my access to the University of Florida HiPerGator research computing cluster. Elizaveta Stovba expertly coordinated the acquisition of high-resolution images for this publication. Sonny Russano provided research assistance with funding from the Center for European Studies at the University of Florida. I am amazed and grateful that Slavic Review was able to find three blind reviewers who waded through an unusually technical text by an unknown colleague to contribute insightful suggestions that have improved the work.
1 “Fotogalereia,” Rossiiskii gosudarstvennyi arkhiv kinofotodokumentov, January 4, 2003, https://web.archive.org/web/20030215101535/http://rgakfd.ru/fotogal.htm (accessed February 13, 2025).
2 The number of works that have made this call are very large at the time of writing. See, for instance, the forum: “Approaches to Decolonization” in Canadian Slavonic Papers 65, no. 2 (2023): 141–244.
3 Susan Smith-Peter, “Periodization as Decolonization,” H-Net, January 4, 2023, https://networks.h-net.org/node/10000/blog/decolonizing-russian-studies/12148542/periodization-decolonization
(accessed February 13, 2025).
4 Computational linguistics is a longstanding field of study whose tools have become more common in humanities disciplines with the advent of accessible platforms for their use. Franco Moretti coined the term “distant reading,” and his collection of articles in the book of the same name, Distant Reading (London, 2013), provides excellent examples of the technique. The number of scholars working along similar lines is hard to count. One notable example is Frank Fischer, et al., “Programmable Corpora: Introducing DraCor, an Infrastructure for the Research on European Drama,” last modified July 10, 2019, in Proceedings of DH2019: “Complexities,” Utrecht University, doi:10.5281/zenodo.4284002 (accessed February 13, 2025). A set of corpora for computational analysis of the structure and text of theatrical works with especially strong datasets in east European languages like Bashkir, Russian, Tatar, and Ukrainian.
5 Taylor Arnold and Lauren Tilton have used this term to describe a toolkit they are developing for large-scale analysis of visual corpora. See Taylor Arnold and Lauren Tilton, Distant Viewing: Computational Exploration of Digital Images (Cambridge, Mass., 2023).
6 Just one example of thousands: Beth McMurtrie and Beckie Supiano, “ChatGPT Has Changed Teaching. Our Readers Tell Us How,” The Chronicle of Higher Education, December 11, 2023, https://www.chronicle.com/article/chatgpt-has-changed-teaching-our-readers-told-us-how (accessed February 13, 2025).
7 R. Darrell Meadows and Joshua Sternfeld, “Artificial Intelligence and the Practice of History: A Forum,” The American Historical Review 128, no. 3 (September 2023): 1345–49. See also the associated articles from the forum.
8 An exception to the lack of digital scholarship in flagship REEES publications is Hilah Kohen, Katherine M. H. Reischl, Andrew Janco, Susan Grunewald, and Antonina Puchkovskaia, “Reading Race in Slavic Studies Scholarship through a Digital Lens,” Slavic Review 80, no. 2 (Summer 2021): 234–44; and Tatyana Gershkovich, Madeline Kehl, and Simon DeDeo, “Public Patterns in Private Writing: Computational Insights into Russophone Diaries,” Russian Review (forthcoming), https://doi.org/10.1111/russ.70026. For a broad overview of the use of artificial intelligence in the field, see Daria Gritsenko, Mikhail Kopotev, and Mariëlle Wijermars, “Digital Russian Studies: An Introduction” in The Palgrave Handbook of Digital Russian Studies edited by Daria Gritsenko, Mariëlle Wijermars, and Mikhail Kopotev (Basingstoke, 2021). See also individual works in part II of this volume. The journal Studies in Russian, Eurasian and Central European New Media, previously known as Digital Icons, has published much innovative research that analyzes online media in the last twenty years, although this research tends to use close reading as its method rather than computational approaches.
9 Lara Putnam, “The Transnational and the Text-Searchable: Digitized Sources and the Shadows They Cast,” The American Historical Review 121, no. 2 (April 2016): 377–402.
10 Benjamin Schmidt, “Representation Learning,” The American Historical Review 128, no. 3 (June 2023): 1350–53.
11 Kate Crawford and Trevor Paglen, “Excavating AI: The Politics of Images in Machine Learning Training Sets,” https://excavating.ai/ (accessed February 18, 2025). See also Andrew Prescott, “Bias in Big Data, Machine Learning and AI: What Lessons for the Digital Humanities?,” Digital Humanities Quarterly 17, no. 2 (2023), http://www.digitalhumanities.org/dhq/vol/17/2/000689/000689.html (accessed February 18, 2025).
12 Joshua Sternfeld, “AI-as-Historian,” The American Historical Review 128, no. 3 (September 2023): 1376.
13 “Obshchaia informatsiia,” Rossiiskii gosudarstvennyi arkhiv kinofotodokumentov, http://rgakfd.ru/obshchaya-informaciya (accessed February 18, 2025).
14 Dateparser—Python Parser for Human Readable Dates, https://dateparser.readthedocs.io/en/latest/ (accessed February 18, 2025).
15 Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, Zbigniew Wojna, “Rethinking the Inception Architecture for Computer Vision,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Las Vegas, 2016): 2818–26. See the appendix for more information on transfer learning.
16 Teachable Machine, https://teachablemachine.withgoogle.com/ (accessed February 18, 2025).
17 Among the many works on aesthetic shifts, Katerina Clark, The Soviet Novel: History as Ritual (Bloomington, 2000), shows the consolidation of the socialist realist canon in the novel under Stalin. The liberalization of culture after Stalin’s death saw an emphasis on sincerity in prose and private writing. See Anatoly Pinsky, “The Diaristic Form and Subjectivity under Khrushchev,” Slavic Review 73, no. 4 (Winter 2014): 805–27.
18 Harish Maringanti, Dhanushka Samarakoon, Bohan Zhu, “Machine Learning Meets Library Archives: Image Analysis to Generate Descriptive Metadata,” https://research.lyrasis.org/server/api/core/bitstreams/e11773df-b65f-4f85-84f2-258860a60264/content (accessed February 18, 2025). For a similar historical image classification project, see Jhe-An Chen, Jen-Chien Hou, Richard Tzong-Han Tsai, Hsiung-Ming Liao, Shih-Pei Chen, Ming-Ching Chang, “Image Classification for Historical Documents: A Study on Chinese Local Gazetteers,” Digital Scholarship in the Humanities 39, no. 1 (April 2024): 61–73.
