Film reviews are an obvious area for the application of sentiment analysis, but while this is common in the field of computer science, it has been mostly absent in film studies. Film scholars have quite rightly been skeptical of such techniques due to their inability to grasp nuanced critical texts. Recent technological developments have, however, given us cause to re-evaluate the usefulness of automated sentiment analysis for historical film reviews. The release of ever more sophisticated Large Language Models (LLMs) has shown that their capacity to handle nuanced language could overcome some of the shortcomings of lexicon-based sentiment analysis. Applying it to historical film reviews seemed logical and promising to us. Some of our early optimism was misplaced: while LLMs, and in particular ChatGPT, proved indeed to be much more adept at dealing with nuanced language, they are also difficult to control and implement in a consistent and reproducible way – two things that lexicon-based sentiment analysis excels at. Given these contrasting sets of strengths and weaknesses, we propose an innovative solution which combines the two, and has more accurate results. In a two-step process, we first harness ChatGPT’s more nuanced grasp of language to undertake a verbose sentiment analysis, in which the model is prompted to explain its judgment of the film reviews at length. We then apply a lexicon-based sentiment analysis (with Python’s NLTK library and its VADER lexicon) to the result of ChatGPT’s analysis, thus achieving systematic results. When applied to a corpus of 80 reviews of three canonical Weimar films (Das Cabinet des Dr. Caligari, Metropolis and Nosferatu), this approach successfully recognized the sentiments of 88.75% of reviews, a considerable improvement when compared to the accuracy rate of the direct application of VADER to the reviews (66.25%). These results are particularly impressive given that this corpus is especially challenging for automated sentiment analysis, with a prevalence of macabre themes, which can easily trigger falsely negative results, and a high number of mixed reviews. We believe this hybrid approach could prove useful for application in large corpora, for which close reading of all reviews would be humanly impossible.
影评显然是情感分析的一个应用领域，但这在计算机科学领域很常见，而在电影研究领域却鲜有应用。电影学者对这类技术持怀疑态度是有道理的，因为它们无法把握细致入微的评论文本。然而，最近的技术发展使我们有理由重新评估自动情感分析对历史影评的有用性。越来越复杂的大型语言模型（LLM）的发布表明，它们处理细微语言的能力可以克服基于词典的情感分析的一些缺点。在我们看来，将其应用于历史影评似乎是合乎逻辑且大有可为的。我们早期的一些乐观看法是错误的：虽然事实证明 LLM，尤其是 ChatGPT，确实更善于处理细微语言，但它们也很难以一致和可重现的方式进行控制和实施，而这两点正是基于词典的情感分析所擅长的。鉴于这些优缺点的对比，我们提出了一种创新的解决方案，将两者结合起来，从而获得更准确的结果。我们分两步进行，首先利用 ChatGPT 对语言更细致入微的把握，进行冗长的情感分析，促使模型详细解释其对影评的判断。然后，我们将基于词典的情感分析（使用 Python 的 NLTK 库及其 VADER 词库）应用于 ChatGPT 的分析结果，从而获得系统性的结果。在对魏玛三部经典电影（《卡里加里博士的小屋》、《大都会》和《诺斯费拉图》）的 80 篇评论语料进行分析时，该方法成功识别了 88.75% 的评论情感，与直接应用 VADER 分析评论的准确率（66.25%）相比有了显著提高。这些结果尤其令人印象深刻，因为这个语料库对于自动情感分析来说特别具有挑战性，因为它普遍存在恐怖主题，很容易引发错误的负面结果，而且存在大量混合评论。我们相信，这种混合方法在大型语料库中的应用会非常有用，因为在大型语料库中，要仔细阅读所有评论是不可能的。
{"title":"Revisiting Weimar Film Reviewers’ Sentiments: Integrating Lexicon-Based Sentiment Analysis with Large Language Models","authors":"Isadora Campregher Paiva, Josephine Diecke","doi":"10.22148/001c.118497","DOIUrl":"https://doi.org/10.22148/001c.118497","url":null,"abstract":"Film reviews are an obvious area for the application of sentiment analysis, but while this is common in the field of computer science, it has been mostly absent in film studies. Film scholars have quite rightly been skeptical of such techniques due to their inability to grasp nuanced critical texts. Recent technological developments have, however, given us cause to re-evaluate the usefulness of automated sentiment analysis for historical film reviews. The release of ever more sophisticated Large Language Models (LLMs) has shown that their capacity to handle nuanced language could overcome some of the shortcomings of lexicon-based sentiment analysis. Applying it to historical film reviews seemed logical and promising to us. Some of our early optimism was misplaced: while LLMs, and in particular ChatGPT, proved indeed to be much more adept at dealing with nuanced language, they are also difficult to control and implement in a consistent and reproducible way – two things that lexicon-based sentiment analysis excels at. Given these contrasting sets of strengths and weaknesses, we propose an innovative solution which combines the two, and has more accurate results. In a two-step process, we first harness ChatGPT’s more nuanced grasp of language to undertake a verbose sentiment analysis, in which the model is prompted to explain its judgment of the film reviews at length. We then apply a lexicon-based sentiment analysis (with Python’s NLTK library and its VADER lexicon) to the result of ChatGPT’s analysis, thus achieving systematic results. When applied to a corpus of 80 reviews of three canonical Weimar films (Das Cabinet des Dr. Caligari, Metropolis and Nosferatu), this approach successfully recognized the sentiments of 88.75% of reviews, a considerable improvement when compared to the accuracy rate of the direct application of VADER to the reviews (66.25%). These results are particularly impressive given that this corpus is especially challenging for automated sentiment analysis, with a prevalence of macabre themes, which can easily trigger falsely negative results, and a high number of mixed reviews. We believe this hybrid approach could prove useful for application in large corpora, for which close reading of all reviews would be humanly impossible.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":" 26","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141827629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mila Oiva, Tillmann Ohm, Ksenia Mukhina, Mar Canet Solà, Maximilian Schich
Newsreels, short documentary news films, were an influential channel of mass communication and propaganda in the Soviet Union. They served as an important means of visualizing the world for audiences in the way the Soviet authorities wanted it to be depicted. Studies in Soviet visual culture have recognized both continuities of repeating patterns and changes in the post-World War II period. This understanding is based primarily on temporally limited source selections, while a more systematic study of the developments in Soviet visual culture over a longer period is pending. In this article, we reveal long-term continuities, subtle changes, and sudden shifts in the official visual discourse in the Soviet newsreel series ‘Novosti dnia’ (News of the Day) 1945 to 1992. We study visual patterns in approximately 1,700 digitized newsreel issues, each about ten minutes long, using multidimensional vector embeddings. These embeddings, produced from the central frames of 205,678 shots, help visually evaluate the footage and assess visual similarities based on ResNet50 feature vectors. For this, we use the Collection Space Navigator tool. The article demonstrates how multidimensional vector embeddings can be used to study the internal time of the films, and the external time of the years running by.
{"title":"Soviet View of the World. Exploring Long-Term Visual Patterns in “Novosti dnia” Newsreel Journal (1945-1992)","authors":"Mila Oiva, Tillmann Ohm, Ksenia Mukhina, Mar Canet Solà, Maximilian Schich","doi":"10.22148/001c.118495","DOIUrl":"https://doi.org/10.22148/001c.118495","url":null,"abstract":"Newsreels, short documentary news films, were an influential channel of mass communication and propaganda in the Soviet Union. They served as an important means of visualizing the world for audiences in the way the Soviet authorities wanted it to be depicted. Studies in Soviet visual culture have recognized both continuities of repeating patterns and changes in the post-World War II period. This understanding is based primarily on temporally limited source selections, while a more systematic study of the developments in Soviet visual culture over a longer period is pending. In this article, we reveal long-term continuities, subtle changes, and sudden shifts in the official visual discourse in the Soviet newsreel series ‘Novosti dnia’ (News of the Day) 1945 to 1992. We study visual patterns in approximately 1,700 digitized newsreel issues, each about ten minutes long, using multidimensional vector embeddings. These embeddings, produced from the central frames of 205,678 shots, help visually evaluate the footage and assess visual similarities based on ResNet50 feature vectors. For this, we use the Collection Space Navigator tool. The article demonstrates how multidimensional vector embeddings can be used to study the internal time of the films, and the external time of the years running by.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":" 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141824387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
How can digital humanities methods reveal the productivity and connectedness of a group of historical individuals linked by displacement from a country? German film exile during National Socialism, 1933-1945, has always been a complex subject to research because of the scattered nature of the sources in the international distribution of archives (Asper, Horak, Hilchenbach). It remains challenging to reconstruct the worldwide dispersed separate flight routes of more than 3000 individuals who worked for the German film industry before 1933. This contribution concerns a list of film exiles collected by the exile researcher and filmmaker Günter Peter Straschek (1942-2009), whose collection of files belongs to the German National Library, German Exile Archive 1933-1945, Frankfurt am Main and was inventoried according to their Normdata. To this end, a database of GND exile data containing names, birth and death dates, professions, and countries of exile was compiled and enriched with data from online resources (Wikidata and IMDb). How can a more comprehensive look at the data reveal the devastating loss for German film (2) and, on the other hand, the collaboration on the flight (3) showing exiles remaining defiant? By incorporating new data from the Straschek Estate, digital methods further enhance historical research findings.
{"title":"A Digital Trail of Rupture. The German Film Exile 1933-1945 in the Data of Günter Peter Straschek","authors":"Imme Klages","doi":"10.22148/001c.118494","DOIUrl":"https://doi.org/10.22148/001c.118494","url":null,"abstract":"How can digital humanities methods reveal the productivity and connectedness of a group of historical individuals linked by displacement from a country? German film exile during National Socialism, 1933-1945, has always been a complex subject to research because of the scattered nature of the sources in the international distribution of archives (Asper, Horak, Hilchenbach). It remains challenging to reconstruct the worldwide dispersed separate flight routes of more than 3000 individuals who worked for the German film industry before 1933. This contribution concerns a list of film exiles collected by the exile researcher and filmmaker Günter Peter Straschek (1942-2009), whose collection of files belongs to the German National Library, German Exile Archive 1933-1945, Frankfurt am Main and was inventoried according to their Normdata. To this end, a database of GND exile data containing names, birth and death dates, professions, and countries of exile was compiled and enriched with data from online resources (Wikidata and IMDb). How can a more comprehensive look at the data reveal the devastating loss for German film (2) and, on the other hand, the collaboration on the flight (3) showing exiles remaining defiant? By incorporating new data from the Straschek Estate, digital methods further enhance historical research findings.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":" 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141824584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The present paper is an attempt at importing network analysis as a method and applying it to a field that has hitherto been examined in different ways: the study of national cinema. The approach was motivated by the perceived conundrum in the existing studies of German cinema that filmhistorical and political history usually do not match. The aim is to open up another perspective on the problem of periodization by looking at the data of film production, more specifically of collaboration. By using a comprehensive data set which is made availavable by the Filmportal, the central internet platform on German film, the approach in this paper is to look at the key creatives involved in the production of a film in the period from 1919 to 1939 and to conceptualize collaboration and connectivity in a (national) film culture through the use of network research methods.
{"title":"Approaching a National Film History through Data. Network Analysis in German Film History","authors":"Malte Hagener, Theresa Blaschke","doi":"10.22148/001c.118499","DOIUrl":"https://doi.org/10.22148/001c.118499","url":null,"abstract":"The present paper is an attempt at importing network analysis as a method and applying it to a field that has hitherto been examined in different ways: the study of national cinema. The approach was motivated by the perceived conundrum in the existing studies of German cinema that filmhistorical and political history usually do not match. The aim is to open up another perspective on the problem of periodization by looking at the data of film production, more specifically of collaboration. By using a comprehensive data set which is made availavable by the Filmportal, the central internet platform on German film, the approach in this paper is to look at the key creatives involved in the production of a film in the period from 1919 to 1939 and to conceptualize collaboration and connectivity in a (national) film culture through the use of network research methods.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":" 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141825838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Digital Film Historiography: Challenges of/and Interdisciplinarity","authors":"Malte Hagener, Diana Roig-Sanz","doi":"10.22148/001c.120944","DOIUrl":"https://doi.org/10.22148/001c.120944","url":null,"abstract":"","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":" 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141826008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a sociologically-oriented study, this project contributes to an archaeology of cinema fandom broadly, and early Spanish fan culture specifically, by spotlighting male readers of popular film magazines. Taking as an exploratory case study reader interactivity with the magazine Popular Film, analysis of correspondence and published photos of readers participating in reader contests demonstrates that the magazine’s cinema fan base was composed of a strikingly large proportion of readers who were male and that these were ardent enthusiasts of celebrity consumer culture. This is a notable contradistinction to the widely-held idea of the star-struck female movie fan. Methodologically, in conducting this study we reflect on the challenges of digital approaches to historical periodical research, where particular challenges are posed when working with magazines in a non-anglophone language, and when there are few baseline studies to rely on to guide and contextualize patterns picked up through strictly macro methods. We advocate for the affordances of a mixed macro-micro approach that combines distant reading with traditional textual studies of close reading. By adopting such a hybrid framework, digital methods provide new opportunities towards reconstructing profiles of magazine readerships and to unearth evidence of male movie fans in Spain.
{"title":"A Digital Archaeology of Early Hispanic Film Culture: Film Magazines and the Male Fan Reader","authors":"Anna Torres-Cacoullos, Elizaveta Senatorova","doi":"10.22148/001c.118152","DOIUrl":"https://doi.org/10.22148/001c.118152","url":null,"abstract":"As a sociologically-oriented study, this project contributes to an archaeology of cinema fandom broadly, and early Spanish fan culture specifically, by spotlighting male readers of popular film magazines. Taking as an exploratory case study reader interactivity with the magazine Popular Film, analysis of correspondence and published photos of readers participating in reader contests demonstrates that the magazine’s cinema fan base was composed of a strikingly large proportion of readers who were male and that these were ardent enthusiasts of celebrity consumer culture. This is a notable contradistinction to the widely-held idea of the star-struck female movie fan. Methodologically, in conducting this study we reflect on the challenges of digital approaches to historical periodical research, where particular challenges are posed when working with magazines in a non-anglophone language, and when there are few baseline studies to rely on to guide and contextualize patterns picked up through strictly macro methods. We advocate for the affordances of a mixed macro-micro approach that combines distant reading with traditional textual studies of close reading. By adopting such a hybrid framework, digital methods provide new opportunities towards reconstructing profiles of magazine readerships and to unearth evidence of male movie fans in Spain.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":" 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141824453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The relationship between on-screen and off-screen inequality in film industries and the relative impact of these on movie attendance is widely discussed but not necessarily empirically demonstrated. This article examines the binary gender composition of film project teams and the gendered representation of film characters as factors for cinema attendance. We collected a unique dataset (N=1285) of all films released during the pre-pandemic decade (2008-2019) in Russia – at that time the largest European cinema market. A marked-up subset of 243 films was used to calculate a novel version of the Bechdel-Wallace test that accounts for the proportion of all non-stereotypical dialogues in the film narration, as opposed to the classical binary test. Our test proves very informative, revealing a strikingly high proportion of dialogues with stereotypical portrayals of women even among the films that pass the Bechdel-Wallace binary threshold. We also undertook a social network analysis (SNA) of the characters’ communications. This analysis demonstrate that women predominantly occupy a peripheral position in film plots. Both stereotyping and marginalization of women are positively related to the proportion of men in the film crew, especially in the role of screenwriter. Simultaneously, having more men in key positions is also correlated with access to larger budgets and better distribution, thus effectively impeding films with stronger women characters from wider audiences. These audiences, however, show no prejudice towards films with such characters: after 2015, films featuring central women protagonists have the same level of attendance as movies without them. Although Russia exemplifies a large non-Western cinema market, the trends we identify, particularly the “gatekeeping” effect of male filmmakers, is notably in line with those observed in Western democracies.
{"title":"Gender (im)balance in the Russian cinema: on the screen and behind the camera","authors":"Xenia Leontyeva, Olessia Koltsova, Deb Verhoeven","doi":"10.22148/001c.116142","DOIUrl":"https://doi.org/10.22148/001c.116142","url":null,"abstract":"The relationship between on-screen and off-screen inequality in film industries and the relative impact of these on movie attendance is widely discussed but not necessarily empirically demonstrated. This article examines the binary gender composition of film project teams and the gendered representation of film characters as factors for cinema attendance. We collected a unique dataset (N=1285) of all films released during the pre-pandemic decade (2008-2019) in Russia – at that time the largest European cinema market. A marked-up subset of 243 films was used to calculate a novel version of the Bechdel-Wallace test that accounts for the proportion of all non-stereotypical dialogues in the film narration, as opposed to the classical binary test. Our test proves very informative, revealing a strikingly high proportion of dialogues with stereotypical portrayals of women even among the films that pass the Bechdel-Wallace binary threshold. We also undertook a social network analysis (SNA) of the characters’ communications. This analysis demonstrate that women predominantly occupy a peripheral position in film plots. Both stereotyping and marginalization of women are positively related to the proportion of men in the film crew, especially in the role of screenwriter. Simultaneously, having more men in key positions is also correlated with access to larger budgets and better distribution, thus effectively impeding films with stronger women characters from wider audiences. These audiences, however, show no prejudice towards films with such characters: after 2015, films featuring central women protagonists have the same level of attendance as movies without them. Although Russia exemplifies a large non-Western cinema market, the trends we identify, particularly the “gatekeeping” effect of male filmmakers, is notably in line with those observed in Western democracies.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":"116 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141001836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
From personal memoirs and cooking recipes to revolutionary agitation and war coverage, the People’s Liberation Army Daily offers a wealth of insights into the sociopolitical and affective realities of post-1949 China. One of the few major periodicals that continued publication during the Cultural Revolution (1966-1976), the journal has received relatively scant attention from scholars, except for political science studies devoted to the PRC propaganda system. Combining close reading and historical analysis with quantitative conceptuality and text mining, we demonstrate how the PLA Daily legitimizes state violence differently through its representation of various soldier figures, the zhanshi, the junren, and the minbing. We also use a large language model to show how the journal distributes violent sentiments to international topics in times of domestic turmoil.
{"title":"Vectors of Violence: Legitimation and Distribution of State Power in the People’s Liberation Army Daily (Jiefangjun Bao), 1956-1989","authors":"Aaron Gilkison, Maciej Kurzynski","doi":"10.22148/001c.115481","DOIUrl":"https://doi.org/10.22148/001c.115481","url":null,"abstract":"From personal memoirs and cooking recipes to revolutionary agitation and war coverage, the People’s Liberation Army Daily offers a wealth of insights into the sociopolitical and affective realities of post-1949 China. One of the few major periodicals that continued publication during the Cultural Revolution (1966-1976), the journal has received relatively scant attention from scholars, except for political science studies devoted to the PRC propaganda system. Combining close reading and historical analysis with quantitative conceptuality and text mining, we demonstrate how the PLA Daily legitimizes state violence differently through its representation of various soldier figures, the zhanshi, the junren, and the minbing. We also use a large language model to show how the journal distributes violent sentiments to international topics in times of domestic turmoil.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":"109 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141035096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this article, I use document embedding models and a training set of nineteenth-century American recipes to build a pipeline classifier for identifying recipes in the broader nineteenth-century newspaper press. The model reveals a much more expansive understanding of the recipe form, which primarily centers around measurement words and prescriptive language rather than a heavily reliance upon the culinary. This fluidity of form allows nineteenth-century writers to harness the recipe form as a tool for political commentary all while no appearing to disrupt the careful divides between the public and domestic spheres. These recipe-adjacent texts, which are both recipe and not, offer a broader picture of short-form political commentary in the nineteenth century which can include genres and forms once thought unable to gestured beyond the confines of the kitchen.
{"title":"What We Didn’t Know a Recipe Could Be: Political Commentary, Machine Learning Models, and the Fluidity of Form in Nineteenth-Century Newspaper Recipes","authors":"Avery Blankenship","doi":"10.22148/001c.115371","DOIUrl":"https://doi.org/10.22148/001c.115371","url":null,"abstract":"In this article, I use document embedding models and a training set of nineteenth-century American recipes to build a pipeline classifier for identifying recipes in the broader nineteenth-century newspaper press. The model reveals a much more expansive understanding of the recipe form, which primarily centers around measurement words and prescriptive language rather than a heavily reliance upon the culinary. This fluidity of form allows nineteenth-century writers to harness the recipe form as a tool for political commentary all while no appearing to disrupt the careful divides between the public and domestic spheres. These recipe-adjacent texts, which are both recipe and not, offer a broader picture of short-form political commentary in the nineteenth century which can include genres and forms once thought unable to gestured beyond the confines of the kitchen.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":"46 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140721077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study investigates the analysis of evaluative linguistic patterns within the context of the German-language Islamophobic online blog PI-News. The corpus consists of texts that refer to the Quran. The innovation of this research lies in two primary dimensions: Firstly, it adopts John Dewey’s pragmatism to establish an explicit valuation theory. Secondly, it extends the boundaries of topic modeling in the digital humanities by integrating van Dijk’s differentiation between aboutness and pragmatic macrostructures of texts. Notably, within these pragmatic macrostructures, the study highlights the practice of quoting Quran suras as a significant linguistic pattern. Together with the analysis of topic distribution and topic pathways in texts, the paper illustrates how evaluative practices reinforce the ideal of an Islam-free Europe.
本研究以德语仇视伊斯兰教的在线博客 PI-News 为背景，对评价性语言模式进行分析。语料库由提及《古兰经》的文本组成。本研究的创新之处主要体现在两个方面：首先，它采用约翰-杜威（John Dewey）的实用主义建立了明确的评价理论。其次，它通过整合 van Dijk 对文本的有关性和实用性宏观结构的区分，扩展了数字人文领域主题建模的边界。值得注意的是，在这些语用宏观结构中，研究强调了引用《古兰经》经文的做法是一种重要的语言模式。结合对文本中话题分布和话题路径的分析，本文说明了评价性实践如何强化了无伊斯兰欧洲的理想。
{"title":"Topic models indicate textual aboutness and pragmatics: Valuation practices in Islamophobic discourse","authors":"Julia Krasselt, Philipp Dreesen","doi":"10.22148/001c.92535","DOIUrl":"https://doi.org/10.22148/001c.92535","url":null,"abstract":"This study investigates the analysis of evaluative linguistic patterns within the context of the German-language Islamophobic online blog PI-News. The corpus consists of texts that refer to the Quran. The innovation of this research lies in two primary dimensions: Firstly, it adopts John Dewey’s pragmatism to establish an explicit valuation theory. Secondly, it extends the boundaries of topic modeling in the digital humanities by integrating van Dijk’s differentiation between aboutness and pragmatic macrostructures of texts. Notably, within these pragmatic macrostructures, the study highlights the practice of quoting Quran suras as a significant linguistic pattern. Together with the analysis of topic distribution and topic pathways in texts, the paper illustrates how evaluative practices reinforce the ideal of an Islam-free Europe.","PeriodicalId":33005,"journal":{"name":"Journal of Cultural Analytics","volume":" 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140218236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：