Topic Modeling, Epistemology, and the English and German Novel

Abstract

According to Rita Felski, context is overrated. Even in the sophisticated variants of contextualization typical of the New Historicism, she explains, scholars' obsession with historical context as the ultimate source of textual meaning disregards the capacity of literature to resonate across time and space. "Why is it," she writes, "that we can feel solicited, button-holed, stirred up, by words that were drafted eons ago?" (576). Felski is not the first to raise such objections. In an essay from 2001, Russell Berman takes a similar approach to the politics of periodization, pointing out how periodizing a work can serve to discipline it, that is to say, to deny its claim on the reader's present. For Berman, "A literary-critical culture that values historical frames over 'artistic pleasure,' . . . tends to dismiss the diachronic moment in any reading, and with it the potential of tradition, the capacity precisely to transcend the constraints of the isolated historical moment." Both Felski and Berman present powerful arguments against the fetishization of contemporaneity as the source of the truth of a work. In their focus on affect, however, they neglect a crucial facet of the transtemporal resonance they seek to underscore. To limit oneself to the question of how and why literature can "solicit," "button-hole," and "stir us up" is to understate its role as both an instrument of cognition and a means of fostering particular cognitive capacities, or at least to sidestep the constitutive role of cognition in the experience of aesthetic pleasure.

Topic extraction using local graph centrality and semantic similarity

“…5,6 Topic extraction and topic modeling can assist in organizing, understanding, and summarizing large text corpus. [7][8][9] Topic extraction identifies sets of words as topics from corpus, representing the information in the corpus. [5][6][7][8] It also addresses another need of text mining by providing a mechanism for obtaining the recurrent patterns in the text.…”

“…[7][8][9] Topic extraction identifies sets of words as topics from corpus, representing the information in the corpus. [5][6][7][8] It also addresses another need of text mining by providing a mechanism for obtaining the recurrent patterns in the text. Topic extraction is used to find the main concepts and relevant words in the text.…”

“…[7][8][9][10][11] Topic extraction has been shown to be effective in addressing challenges in information retrieval, visualization of data, linguistic modeling, and machine processing of linguistic artifacts. [5][6][7][8][9][10][11] Topic extraction is also used in sentiment analysis, social network analysis, digital humanities, social sciences, and healthcare domain. [12][13][14][15][16][17][18] Both supervised and unsupervised methods exist for topic extraction.…”

Topic models do not model topics: epistemological remarks and steps towards best practices

“…It was initially developed and continues to be used for information retrieval and text classification purposes in applied contexts (Bao et al, 2009;Asuncion et al, 2010;Ramage et al, 2011;Wang and Blei, 2011;Chuang et al, 2013;Si et al, 2014;Zhong et al, 2015;van Der Hooft et al, 2016;Liu et al, 2016;Boyd-Graber et al, 2017;Kuhn, 2018;Liu et al, 2019;Reber, 2019;Korfiatis et al, 2019, and many others). More recently, it has also gained momentum in the context of so-called distant reading 2 in the digital humanities and social sciences, where it is now increasingly being used to answer subject-specific research questions regarding the distributions of content in literary text (Asgari et al, 2013;Tangherlini and Leonard, 2013;Jockers and Mimno, 2013;Underwood, 2014;Goldstone and Underwood, 2014;Weitin and Herget, 2017;Mitrofanova and Sedova, 2017;Schöch, 2017;Erlin, 2018;Navarro-Colorado, 2018;Jacobs, 2018;Sieg, 2019;Dahllöf and Berglund, 2019;Liu and Jin, 2020), court decisions (Livermore et al, 2016;Panagis et al, 2016;Carter et al, 2016;Law, 2016;Wang et al, 2017;Rice, 2017;Young, 2019;Lampach and Dyevre, 2018), political and legal debate (Young, 2012;…”