Från ordfrekvenser till generativa modeller
Metodologisk reflektion kring datadrivna analyser av litteraturkritik
DOI:
https://doi.org/10.54797/tfl.v55i4.59781Nyckelord:
literary criticism, generative models, topic modelling, book reviewing, word frequencies, discourse analysisAbstract
From Word Frequencies to Generative Models: Methodological Reflections on Data-Driven Analyses of Literary Criticism
In this article, we discuss the possibilities and limitations of three different data-driven methods for replicating an earlier study in literary scholarship, Lina Samuelsson’s Kritikens ordning: Svenska bokrecensioner 1906, 1956 och 2006 (2013). We employ methods that can be said to correspond to three phases of language technology development in order to analyse research material selected according to the same principles as in Samuelsson’s study, but on a larger scale. For copyright reasons, these experiments were carried out on our material from the early 20th century.
Drawing on the Russian Formalist Viktor Shklovsky’s concept of “defamiliarisation”, we emphasise the potential of data-driven methods to create a distancing effect that prompts different perspectives on familiar research material. Beginning with word frequency analysis, we show how a simple quantitative method can contribute interesting yet methodologically rigid perspectives on a collection of book reviews. We proceed by describing how topic modelling produces results that appear analytically flat but can nonetheless sharpen the analytical gaze on the material. Finally, we show how generative language models can contribute with substantial analytical perspectives on patterns of evaluation in literary criticism, while at the same time introducing a distinct level of methodological complexity. In conclusion, we suggest that the use of data-driven methods in literary studies calls for critical reflection not only on digital and traditional methods individually, but also on the interplay between them.
Finally, we show how generative language models can contribute with substantial analytical perspectives on patterns of evaluation in literary criticism, while at the same time introducing a distinct level of methodological complexity. In conclusion, we suggest that the use of data-driven methods in literary studies calls for critical reflection not only on digital and traditional methods individually, but also on the interplay between them.
Nedladdningar
Referenser
Agrell, Beata. ”Konsten som grepp – formalistiska strategier och emblematiska tankeformer”. Tidskrift för Litteraturvetenskap vol. 26 (1997:1), 26–58.
Bednarek, Monika. ”Topic Modelling in Corpus-Based Discourse Analysis. Uses and Critiques”. Discourse Studies vol. 27 (2024:4), 1–13. https://doi.org/10.1177/14614456241293075.
Blei, David M., Ng, Andrew Y. & Jordan, Michael I. ”Latent Dirichlet Allocation”. Journal of Machine Learning Research vol. 3 (2003:1), 993–1022.
Bonezzi, Andrea, Ostinelli, Massimiliano, Melzne, Johann. ”The Human Black-Box.The Illusion of Understanding Human Better Than Algorithmic Decision-Making”. Journal of Experimental Psychology: General vol. 151 (2022:9), 2250–2258. https://doi.org/10.1037/xge0001181.
Brodén, Daniel, Ingvarsson, Jonas, Samuelsson, Lina & Wåhlstrand Skärström, Victor. ”Visualization as Defamiliarization. Mixed Methods Approaches to Historical Book Reviews”. Journal of Computational Literary Studies vol. 3 (2024:1), 1–26. https://doi.org/10.48694/jcls.3926
Brodén, Daniel, Samuelsson, Lina & Alfter, David. ”Retouching and Refiguring Literary Criticism. Experiments with a Generative Model for Analyzing Book Reviews”. I Flows & Frictions. Mixed Methods for AI-Driven Research on Historical Media, red. Daniel Brodén & Lina Samuelsson, 93–114. Göteborg: LIR.Skrifter, 2026.
Brookes, Gavin & McEnery, Tony. ”The Utility of Topic Modelling for Discourse Studies. A Critical Evaluation”. Discourse Studies vol. 21 (2019:1), 1–21. https://doi.org/10.1177/1461445618814032.
Campello, Ricardo J. G. B., Moulavi, Davoud & Sander, Joerg. ”Density-Based Clustering Based on Hierarchical Density Estimates”. I Advances in Knowledge and Data Mining. PAKDD 2013. Lecture Notes in Computer Science vol. 7819, red. Jian Pei, Vincent S. Tseng, Longbing Cao, Hiroshi Motada, Guandong Xu, 160–172. Berlin/Heidelberg: Springer, 2013. https://doi.org/10.1007/978-3-642-37456-2_14.
Esposito, Elena. Artificial Communication. How Algorithms Produce Social Intelligence. Boston: MIT Press, 2022. https://doi.org/10.7551/mitpress/14189.001.0001
Forser, Tomas. Kritiken av kritiken. 1900-talets svenska litteraturkritik. Gråbo: Antrophos, 2002.
Golgoon, Ashkan, Filom, Khashayar, Ravi Kannan, Arjun. ”Mechanistic Interpretability of Large Language Models with Applications to the Financial Services Industry”. arXiv:2407.11215, 2024, 1–23. https://doi.org/10.48550/arXiv.2407.11215.
Grootendorst, Maarten R. ”BERTopic. Neural topic modeling with class-based TF-IDF procedure”, arXiv:2203.05794, 2022.
Grzybowski, Andrzej, Pawlikowska-Łagód, Katarzyna, Lamber, W. Clark. ”A History of Artificial Intelligence”. Clinics in Dermatology vol 42 (2024:3), 221–229. https://doi.org/10.1016/j.clindermatol.2023.12.016.
Ingvarsson, Jonas. Towards a Digital Epistemology. Aesthetics and Modes of Thought in Early Modernity and the Present Age, 2:a utg. Cham: Palgrave Macmillan, 2021.
McInnes, Leland, Healy, John & Melville, James. ”UMAP. Uniform Manifold Approximation and Projection for Dimension Reduction”. arXiv:1802.03426, 2020.
Malmsten, Martin, Börjeson, Love & Haffenden, Chris. ”Playing with Words at the National Library of Sweden – Making a Swedish BERT”. arXiv:2007.01658, 2020.
Oberbichler, Sarah, Boroş, Emanuela, Doucet, Antoine, Marjanen, Jani, Pfanzelter, Eva, Rautiainen, Juha, Toivonen, Hannu & Tolonen, Mikko. ”Integrated Interdisciplinary Workflows for Research on Historical Newspapers. Perspectives from Humanities Scholars, Computer Scientists, and Librarians”. Journal of the Association for Information Science and Technology vol. 73 (2022:2), 225–239. https://doi.org/10.1002/asi.24565.
Piper, Andrew. Can We Be Wrong? The Problem of Textual Evidence in a Time of Data. Cambridge, Mass.: Cambridge University Press, 2020.
Ramsay, Stephen. Reading Machines. Toward an Algorithmic Criticism. Chicago: University of Illinois Press, 2011.
Riffaterre, Michael. ”Litteraturkritikkens diskurs”. Claus Østergaard övers. Ny poetik. Tidsskrift for litteraturvidenskab 3 (1994), 97–110.
Samuelsson, Lina. Kritikens ordning. Svenska bokrecensioner 1906, 1956, 2006. Karlstad: Bild, text & form, 2013.
Samuelsson, Lina, Brodén, Daniel, Ingvarsson, Jonas & Wåhlstrand, Victor. ”Kritikens ordning visualiserad. Mixade metoder i studiet av bokrecensioner”. Samlaren. Tidskrift för forskning om svensk och annan nordisk litteratur vol. 145 (2024), 330–354.
Sklovskij, Viktor. ”Konsten som grepp”. Bengt A. Lundberg övers. I Form och struktur, red. Kurt Aspelin och Bengt A. Lundberg, 45–63. Stockholm: PAN/Norstedt, [1916] 1971.
Tangherlini, Timothy & Leonard, Peter. “Trawling in the Sea of the Great Unread. Sub-corpus Topic Modeling and Humanities research”. Poetics vol. 41 (2013:6): 725–749. https://doi.org/10.1016/j.poetic.2013.08.002.
Törnberg, Anton. ”Towards a Third Generation of Natural Language Processing. Enhancing Qualitative Research with Large Language Models”. I Flows & Frictions. Mixed Methods for AI-Driven Research on Historical Media, red. Daniel Brodén & Lina Samuelsson, 35–56. Göteborg: LIR Skrifter, 2026.
Underwood, Ted. Distant Horizons. Digital Evidence and Literary Change. Chicago: University of Chicago Press, 2019.
Underwood, Ted, Nelson, Laura K., Wilkens, Matthew. ”Can Language Models Represent the Past Without Anachronism?” arXiv:2505.00030, 2025, 1–13.
https://doi.org/10.48550/arXiv.2505.00030.
Recensioner
B. B–m [Birger Bæckström]. ”Boknytt”. Göteborgs-Posten, 1906-09-17.
B. B–m [Birger Bæckström]. ”Boknytt”. Göteborgs-Posten, 1906-11-26.
B. B–n [Bo Bergman], ”Svensk prosakonst”. Dagens Nyheter, 1905-11-19.
B. B–n [Bo Bergman]. ”Svensk prosakonst”. Dagens Nyheter, 1906-05-21.
J. B–tt. ”En rysk officersroman”. Göteborgs Handels- och Sjöfartstidning, 1906-09-26.
K. E. F., ”Litteratur”. Social-Demokraten, 1906-06-16.
”Korta anmälningar”. Dagens Nyheter, 1905-02-05.
Levertin, Oscar. ”Litteratur”. Svenska Dagbladet, 1906-07-29.
Levertin, Oscar. ”Litteratur”. Svenska Dagbladet, 1906-03-11.
”Litteratur”. Sydsvenska Dagbladet Snällposten, 1906-06-17.
M–z K. ”Vind och vågor”. Vårt Land, 1906-02-03.
–n. ”En rysk militärroman”. Dagens Nyheter, 1906-08-15.
–nn. ”Hilligenlei”. Nya Dagligt Allehanda, 1906-05-23.
O. B. ”Jesu lif enligt Gustaf Frenssens ‘Hilligenlei’”. Vårt Land, 1906-05-18.
–pt– [Hans Emil Larsson]. ”Litteratur”. Sydsvenska Dagbladet Snällposten, 1906-06-21.
Rbg. ”Bokvärlden”. Göteborgs Handels- och Sjöfartstidning, 1906-06-07.
Publicerad
Referera så här
Licens
Copyright (c) 2026 Lina Samuelsson, Daniel Brodén, David Alfter, Aram Karimi
Det här verket är licensierat under en Creative Commons Erkännande 4.0 Internationell-licens.
Författaren/författarna behåller copyright till verket
