Search

Analyzing poetry with automatic tools has great potential for improving verse-related research. Over the last few decades, this field has expanded notably and a large number of tools aiming at analyzing various aspects of poetry have been developed. However, the concrete connection between these tools and traditional scholars investigating poetry and metrics is often missing. The purpose of this article is to bridge this gap by providing a comprehensive survey of the automatic poetry analysis tools available for European languages. The tools are described and classified according to the language for which they are primarily developed, and to their functionalities and purpose. Particular attention is given to those that have open-source code or provide an online version with the same functionality. Combining more traditional research with these tools has clear advantages: it provides the opportunity to address theoretical questions with the support of large amounts of data; also, it allows for the development of new and diversified approaches. [ABSTRACT FROM AUTHOR]

Abstract Understanding the nature–culture entanglement by combining the methods of natural sciences and humanities is little approached in neither of the fields. With a specific combination of methods from both digital humanities and ecology, we aimed at identifying several of people's life circumstances that relate to their individual sensitivity towards biodiversity. The circumstances with a strong correlation could be considered and targeted by decision‐makers, for example by developing specific education programmes for making people more eco‐conscious or adjusting relevant regulations. We applied machine learning techniques onto a database including information about the frequency of biodiversity mentioned in creative literature (BiL) from 1705 to 1969 as response variable related to metadata about the corresponding works and their authors as predictors, including localisation, age, gender and literature genre. The algorithm determined the response's dependency on each predictor, which can be interpreted as the intensity of this particular sensitivity parameter for biodiversity, and which we also related to time. We recognised that gender, age, region and settlement size are predictors significantly correlated to BiL. Statistically, these predictors can be viewed as starting points of the eventual individual level of awareness for biodiversity. For example, authors from villages exhibit a higher BiL than those from cities, which we interpret as a signal for the dependence of awareness for biodiversity on spatial distance from nature, which in turn can be addressed in urban development. Our conclusion is that applying a machine learning technique on literary data yields meaningful results, thereby showing potential for further similar investigations and the combination of methods from natural sciences and humanities to achieve so far unattainable insights. With our study, these insights could contribute to ecologically based decision‐making processes. Read the free Plain Language Summary for this article on the Journal blog.

Understanding the nature–culture entanglement by combining the methods of natural sciences and humanities is little approached in neither of the fields. With a specific combination of methods from both digital humanities and ecology, we aimed at identifying several of people's life circumstances that relate to their individual sensitivity towards biodiversity. The circumstances with a strong correlation could be considered and targeted by decision‐makers, for example by developing specific education programmes for making people more eco‐conscious or adjusting relevant regulations.We applied machine learning techniques onto a database including information about the frequency of biodiversity mentioned in creative literature (BiL) from 1705 to 1969 as response variable related to metadata about the corresponding works and their authors as predictors, including localisation, age, gender and literature genre. The algorithm determined the response's dependency on each predictor, which can be interpreted as the intensity of this particular sensitivity parameter for biodiversity, and which we also related to time.We recognised that gender, age, region and settlement size are predictors significantly correlated to BiL. Statistically, these predictors can be viewed as starting points of the eventual individual level of awareness for biodiversity. For example, authors from villages exhibit a higher BiL than those from cities, which we interpret as a signal for the dependence of awareness for biodiversity on spatial distance from nature, which in turn can be addressed in urban development.Our conclusion is that applying a machine learning technique on literary data yields meaningful results, thereby showing potential for further similar investigations and the combination of methods from natural sciences and humanities to achieve so far unattainable insights. With our study, these insights could contribute to ecologically based decision‐making processes. Read the free Plain Language Summary for this article on the Journal blog. Read the free Plain Language Summary for this article on the Journal blog. [ABSTRACT FROM AUTHOR]

In connection to literature, negative empathy is a sophisticated form of narrative empathy with fictional characters portrayed as markedly evil and seductive at the same time. Several studies on narrative engagement have explored negative empathy mainly from a theoretical perspective. Conversely, empirical approaches have rarely delved into the dynamics of the linguistic construction of the texts studied. To fill this gap, this paper employs computational techniques to investigate the language of a corpus of novels whose characters are particularly apt for the arousal of negative empathy. More specifically, this study uses Sentiment and Emotion Analysis to explore the lexical representation of emotions and to locate fluctuations in the emotional content of the texts. The ultimate aim is to assess both the potential and the vulnerabilities of Sentiment Analysis for detecting emotional shifts in a literary text and thus for revealing the intensity of its emotional content, which may facilitate the readers' morally challenging engagement with negative characters. [ABSTRACT FROM AUTHOR]

In my contribution, I argue that a fruitful integration of computational network analytic methods into literary studies depends on how the ›interaction‹ of two characters in an abstract character network is formalized. I support this hypothesis by using the examples of co-presence, co-reference, and knowledge networks, which I analyze in Heinrich Kleist's tragedy Die Familie Schroffenstein (1803). I assume that the co-presence of characters can provide the basis for more specific formalizations of interaction. But due to its basal specification of interaction, co-presence networks can only be integrated into rather limited questions of literary studies. I illustrate this circumstance by examining Franco Moretti's approach in his essay Network Theory, Plot Analysis (2011): How does he connect his network analyses to concepts of literary studies? How does he reflect his methods? Which observational stance does he adopt? How appropriate is his approach to the object of study? And how does he tie his results back to literary theory? Moretti's explorations show that his network analyses seem to be incompatible with established conceptions of characters – at least partially. Therefore, he demands a new conceptualization of dramatic characters in literary studies. To me, however, it seems to be more productive to put into perspective or enhance – under the auspices of network analysis – existing quantitative aspects of established character presentation (configuration, constellation). I therefore propose two additional formalizations of character interaction to create dramatic networks: co-references and knowledge transfers. Regular co-presence networks, which have widely been tested and discussed among (computational) literary scholars, will serve as a ground of comparison. I illustrate the merits and limitations of co-presence networks on both a single text analysis of Die Familie Schroffenstein and a larger corpus analysis of 587 German-language plays. Cursorily, I present the operationalization of co-references and knowledge transfers. The linguistic concept of co-reference means that two or more linguistic expressions refer to the same entities. A knowledge transfer, in my understanding, is a transmission of new information from at least one literary character to at least one other character. Manual annotations of co-reference chains and knowledge transfers serve as basis for the subsequent network creation. I compare these different manifestations of character interaction in terms of the resulting network visualizations as well as of various mathematical network metrics. The goal is to elicit how useful these two criteria are regarding drama analysis, e. g., the analysis of character properties, and to what extent they can complement, differentiate, or even replace the established co-presence networks. Co-presence, co-reference and knowledge networks reveal different aspects of the characters under consideration, picture different dramatic structures, and place different groups of characters at the center of the networks. Therefore, the three abstract textual representations seem to complement each other. In my article, I show that the extent to which the various criteria can be integrated into research questions of literary studies ought to be discussed on (at least) two levels. Firstly, it is necessary to ask how interesting, relevant, and informative a specific criterion is for one's own research and whether it can relate to the terminology of literary studies. Secondly, it is important to consider how precise the respective criteria can be annotated manually and, subsequently, if and how reliable they can be annotated automatically. [ABSTRACT FROM AUTHOR]

In this article, we provide an overview of machine learning as it is applied in computational literary studies, the field of computational analysis of literary texts and literature related phenomena. We survey a number of scientific publications for the machine learning methodology the scholars used and explain concepts of machine learning and natural language processing while discussing our findings. We establish that besides transformer-based language models, researchers still make frequent use of more traditional, feature-based machine learning approaches; possible reasons for this are to be found in the challenging application of modern methods to the literature domain and in the more transparent nature of traditional approaches. We shed light on how machine learning-based approaches are integrated into a research process, which often proceeds primarily from the non-quantitative, interpretative approaches of non-digital literary studies. Finally, we conclude that the application of large language models in the computational literary studies domain may simplify the application of machine learning methodology going forward, if adequate approaches for the analysis of literary texts are found. [ABSTRACT FROM AUTHOR]

The incorporation of the humanities into digital transformation processes resulted in the emergence of a new research field called digital humanities. This new field has its origin in the beginning of the second half of the twentieth century. From the research point of view, through the analysis of the scientific production of the main academic databases, we provide here an overview of the international panorama of digital humanities, looking at the main countries, institutions, areas of knowledge and leading topics in this discipline. [ABSTRACT FROM AUTHOR]

The article sets up a critique of Sentiment Analysis (SA) tools in literary studies, both from a theoretical and a computational point of view. In the first section, a possible use of SA in narratology and reader response studies is discussed, highlighting the gaps between literary theories and computational models, and suggesting possible solutions to fill them. In the second section, a stratified taxonomy of SA tools is proposed, which distinguishes: (1) the emotion theory adopted by the tool; (2) the method used to build the emotion resources; (3) the technique adopted to accomplish the analysis. A critical survey of six representative SA tools for literary studies (Syuzhet, Vader, SentiArt, SEANCE, Stanford SA, and Transformers Pipelines) closes the article. The article sets up a critique of Sentiment Analysis (SA) tools in literary studies, both from a theoretical and a computational point of view. [ABSTRACT FROM AUTHOR]

The aim of this paper is to present the new CapekDraCor corpus and the DraCor project with its research-oriented concept of a programmable corpora focused on quantitative analyses within the framework of computational literary studies. This digital platform extends the possibilities of large-scale drama analysis with a focus on the dramatic character(s). The basic operationalisation is the interaction within a dramatic configuration, i.e., the scenic co-presence of two speakers, from which network data are automatically extracted, both global networks of interactions of dramas and data characterising individual actors, i.e., literary characters. The paper demonstrates the CapekDraCor corpus, a new contribution to the extensive DraCor database, and presents the way the data are processed with respect to their specific multi-layered structure. The corpus contains all the plays written by Karel and Josef Čapek and the data are processed in a standardized format based on XML and general TEI guidelines for processing drama with a defined basic drama tagset. CapekDraCor also uses the newly created EZdrama format for data processing, which works as an intermediate step from.txt to.xml file as a lightweight YAML-like markup language. A file in this format can be automatically converted into a DraCor-ready XML file with a TEI header. The advantage of the programmable corpora concept is the possibility to use suitably structured data for drama research outside the DraCor platform and with other methods or tools for textual analysis. Simultaneously, this approach moves the researcher from the technical requirements of the analysis to operationalised computational analysis based on research questions and pre-prepared and flexible tools. DraCor is a unique open infrastructure (both in terms of data and tools) for the analysis of European drama, currently comprising 15 corpora in 10 different languages with a total of about 3,000 plays from a wide range of periods. [ABSTRACT FROM AUTHOR]

What do characters in theater plays know about character relations, and how does the distribution of knowledge evolve over the course of a play? We present a dataset of 30 German plays annotated with information about the distribution of knowledge about character relations (such as "A learns from B that C is the parent of D"). All plays were manually annotated by two independent annotators as part of the Q:TRACK research project, which aims to systematically model character knowledge. The dataset is available on GitHub and Zenodo and can be reused, for example, for systematic studies of knowledge in plays or for analyzing disagreements between annotators.

In recent years, Romanian literary studies took one of its major methodological turns toward distant reading, using either or both quantitative and computational analysis. While quantitative analysis employed lexicographical instruments such as dictionaries and literary chronologies, computational analysis tried to approach the issue from a “data rich” historical perspective (Katherine Bode), while also attempting to build a digital corpus adapted to computational methods. The following paper attempts to survey the main research projects that deal with the computational analysis of Romanian literature in general and the Romanian novel in particular. The first part of the study undertakes a succinct state-of-the-art on past and ongoing endeavours concerned with digital approaches to the study of Romanian literature, their initial findings and potential. The second part will take a more theoretic approach to some of the key concepts related to data supported literary history. Finally, the last part of the study tackles the main challenges of developing a digital corpus of a local literature and the shortcomings related to this literature’s “locality” in terms of computational approaches and the compatibility of the tools developed by Western research projects.

We introduce childPoeDE: the first corpus of German poetry for children comprising poems which are still read today and cover a wide range of topics and authors. ChildPoeDE contains poem texts and both poem-level and token-level metadata. Poemlevel metadata includes information about the anthologies and authors, quantitative text features, rhyme and lexical richness. Token-level metadata covers word length, position and frequency, parts-of-speech, onomatopoeia and sonority. This corpus can be used for computational text analysis, but also as a source for stimulus material in experimental studies. The corpus metadata is freely accessible via Zenodo. The poem texts are protected by copyright. [ABSTRACT FROM AUTHOR]

The TRANSCOMP Dataset of Literary Translations is a collection of document-level word frequencies sampled from 10,631 translations into English of global literary fiction published since 1950, together with a historically matched parallel corpus of 10,682 fictional works originally published in English. We provide CSV files with word frequency counts for 10,000-word samples taken from each text. The associated metadata is available in a separate CSV. These data will be useful to literary scholars and linguists working in translation studies, and those interested in the linguistic, stylistic, and thematic specificity of translations from particular regions.

Abstract Nature's non‐material contributions to people are difficult to quantify and one aspect in particular, nature's contributions to communication (NCC), has so far been neglected. Recent advances in automated language processing tools enable us to quantify diversity patterns underlying the distribution of plant and animal taxon labels in creative literature, which we term BiL (biodiversity in literature). We assume BiL to provide a proxy for people's openness to nature's non‐material contributions enhancing our understanding of NCC. We assembled a comprehensive list of 240,000 English biological taxon labels. We pre‐processed and searched a subcorpus of digitised literature on Project Gutenberg for these labels. We quantified changes in biodiversity indices commonly used in ecological studies for 16,000 books, encompassing 4,000 authors, as proxies for BiL between 1705 and 1969. We observed hump‐shape patterns for taxon label richness, abundance and Shannon diversity indicating a peak of BiL in the middle of the 19th century. This is also true for the ratio of biological to general lexical richness. The variation in label use between different sections within books, quantified as β‐diversity, declined until the 1830s and recovered little, indicating a less specialised use of taxon labels over time. This pattern corroborates our hypothesis that before the onset of industrialisation BiL may have increased, reflecting several concomitant influences such as the general broadening of literary content, improved education and possibly an intensified awareness of the starting loss of biodiversity during the period of romanticism. Given that these positive trends continued and that we do not find support for alternative processes reducing BiL, such as language streamlining, we suggest that this pronounced trend reversal and subsequent decline of BiL over more than 100 years may be the consequence of humans’ increasing alienation from nature owing to major societal changes in the wake of industrialisation. We conclude that our computational approach of analysing literary communication using biodiversity indices has a high potential for understanding aspects of non‐material contributions of biodiversity to people. Our approach can be applied to other corpora and would benefit from additional metadata on taxa, works and authors. A free Plain Language Summary can be found within the Supporting Information of this article.

We introduce childPoeDE: the first corpus of German poetry for children comprising poems which are still read today and cover a wide range of topics and authors. ChildPoeDE contains poem texts and both poem-level and token-level metadata. Poem-level metadata includes information about the anthologies and authors, quantitative text features, rhyme and lexical richness. Token-level metadata covers word length, position and frequency, parts-of-speech, onomatopoeia and sonority. This corpus can be used for computational text analysis, but also as a source for stimulus material in experimental studies. The corpus metadata is freely accessible via Zenodo. The poem texts are protected by copyright.

In recent years, Romanian literary studies took one of its major methodological turns toward distant reading, using either or both quantitative and computational analysis. While quantitative analysis employed lexicographical instruments such as dictionaries and literary chronologies, computational analysis tried to approach the issue from a "data rich" historical perspective (Katherine Bode), while also attempting to build a digital corpus adapted to computational methods. The following paper attempts to survey the main research projects that deal with the computational analysis of Romanian literature in general and the Romanian novel in particular. The first part of the study undertakes a succinct state-of-the-art on past and ongoing endeavours concerned with digital approaches to the study of Romanian literature, their initial findings and potential. The second part will take a more theoretic approach to some of the key concepts related to data supported literary history. Finally, the last part of the study tackles the main challenges of developing a digital corpus of a local literature and the shortcomings related to this literature's "locality" in terms of computational approaches and the compatibility of the tools developed by Western research projects. [ABSTRACT FROM AUTHOR]

This dataset covers 41,341 manual event annotations of six German prose texts from the 19th and early 20th century comprising 290,997 tokens. For each text, the dataset includes annotations by two annotators and gold standard annotations. These annotations were used for the automation of narratological event annotations (Vauth, Hatzel, Gius, & Biemann, 2021), a reflection of inter annotator agreements in literary studies (Gius & Vauth, 2022) and the development of an event based plot model (Gius & Vauth, accepted).

MiMoText is a research project in computational literary studies dealing with new ways to model and analyse literary history and literary historiography. It is based on the idea of extracting statements relevant to literary history from bibliographies, scholarly publications and primary sources, in order to build a shared knowledge network for literary history. We employ methods from information extraction and text mining to obtain large numbers of statements about authors and literary works from our data. Moreover, we use the Linked Open Data paradigm to model, represent and query the information we obtain. We believe our project is a step towards a mode of digital humanities that goes not only beyond small, deeply encoded datasets and their close reading, but also beyond Big Data approaches that cannot always be easily adapted to the humanities. Instead, we propose a third way for digital humanities that develops quantitative methods to create and analyse datasets relevant to research in the humanities that are both larger and smarter than has been customary up until recently. [ABSTRACT FROM AUTHOR]

The present study proposes an experimental exploration of the Romanian novel written between 1920 and 1940 through the use of stylometry, a method of distant reading employed for the statistical analysis of style. Drawing from the most recent advances in the field of computational stylistics, we select a formal standpoint from which we seek to investigate the relation between the Romanian novelistic canon and minor, tertiary novels published in the same period. In our test cases, we will attempt to establish some of the more promising aspects of stylometric analysis, as well as single out the experiments that yield no relevant result. Because of the relative novelty of the method, the purpose of our investigations is to offer a kind of pilot experiment that can illustrate the benefits of using computational methods on Romanian literary corpora.

The TRANSCOMP Dataset of Literary Translations is a collection of document-level word frequencies sampled from 10,631 translations into English of global literary fiction published since 1950, together with a historically matched parallel corpus of 10,682 fictional works originally published in English. We provide CSV files with word frequency counts for 10,000-word samples taken from each text. The associated metadata is available in a separate CSV. These data will be useful to literary scholars and linguists working in translation studies, and those interested in the linguistic, stylistic, and thematic specificity of translations from particular regions. [ABSTRACT FROM AUTHOR]

This dataset covers 41,341 manual event annotations of six German prose texts from the 19th and early 20th century comprising 290,997 tokens. For each text, the dataset includes annotations by two annotators and gold standard annotations. These annotations were used for the automation of narratological event annotations (Vauth, Hatzel, Gius, & Biemann, 2021), a reflection of inter annotator agreements in literary studies (Gius & Vauth, 2022) and the development of an event based plot model (Gius & Vauth, accepted). [ABSTRACT FROM AUTHOR]

Since Franco Moretti coined the successful term distant reading, quantitative/computational text analysis methods have gained wide circulation in literary studies. The diffusion of distant reading approaches has raised a lively debate and has attracted various criticisms, both from “traditional literary scholars” and from self-critical adopters. One important reason underlying these critical positions is the fact that it lacks sound and coherent rationales from the point of view of the theory: distant reading is the first methodology in literary studies that does not come with a theory of literature embedded in it. Consequently, all distant reading studies derive their theoretical frameworks and terms from literary theories that mostly rely on the notion that literary texts can be explained only by the way of interpretation. On what grounds, then, can we construct a theory of literature amenable to distant reading methods? I think that the better theoretical frameworks are the cognitive and bio-evolutionistic approaches to literature and cultural evolution studies. These theoretical approaches require a change in the level of description of the literary domain and justify the move from "interpretation" to "explanation" as the real aim of the scholarly inquiry.

The taxon label richness analysed so far (Figure 7, top left) represents the richness of taxon labels, ignoring the correlation to their actual taxon and thus including and distinguishing synonyms. Only one other frame within the corpus, contained in a book of animal anecdotes (Goodrich, 1845), exceeds 100 taxon labels gl Similar to a rank abundance curve in ecology, Figure 4 shows the one hundred most abundant taxon labels in the corpus, representing about two thirds of all occurrences of taxon labels. If we compare the richness trend of taxon labels to the development of the general lexical richness (Figure 7, bottom left) by calculating the ratio of taxon labels' richness and lexical richness (Figure 7, bottom right), we observe a relative decrease in taxon labels. Keywords: biodiversity in literature; computational literary studies; cultural ecosystem services; environmental humanities; historical biodiversity; Nature's Contributions to People; non-material contribution; text mining EN biodiversity in literature computational literary studies cultural ecosystem services environmental humanities historical biodiversity Nature's Contributions to People non-material contribution text mining 1093 1109 17 10/11/21 20211001 NES 211001 INTRODUCTION Our planet is losing biodiversity at unprecedented rates due to land-use change, direct exploitation, climate change, pollution and the invasion of exotic species (Cardinale et al., 2012; IPBES, 2019; Millennium Ecosystem Assessment, 2005; Tilman, 1999). 31.6% of all frames contained no taxon label and 6.5% of all frames contained 10 or more taxon labels. [Extracted from the article]

Scholars working within computational literary studies often invoke Russian Formalism as a methodologically like-minded school of thought and a repository of useful insights, which can at last be tested with the help of recently developed digital techniques. Yet the two formalisms diverge starkly when it comes to three of their most fundamental categories of analysis: first, in their respective conceptions of literary form itself; next, in their notions of history and of what it means to tell the history of form; and finally, in the ways in which they construe the relationship between literature and society as a whole, or, in other words, in their corresponding sociologies of literary form. This paper, then, is a contribution to creating the conditions for the possibility of a genuine exchange between the two formalisms here at issue by focusing, first and foremost, on what divides them. [ABSTRACT FROM AUTHOR]

There is a set of statistical measures developed mostly in corpus and computational linguistics and information retrieval, known as keyness measures, which are generally expected to detect textual features that account for differences between two texts or groups of texts. These measures are based on the frequency, distribution, or dispersion of words (or other features). Searching for relevant differences or similarities between two text groups is also an activity that is characteristic of traditional literary studies, whenever two authors, two periods in the work of one author, two historical periods or two literary genres are to be compared. Therefore, applying quantitative procedures in order to search for differences seems to be promising in the field of computational literary studies as it allows to analyze large corpora and to base historical hypotheses on differences between authors, genres and periods on larger empirical evidence. However, applying quantitative procedures in order to answer questions relevant to literary studies in many cases raises methodological problems, which have been discussed on a more general level in the context of integrating or triangulating quantitative and qualitative methods in mixed methods research of the social sciences. This paper aims to solve these methodological issues concretely for the concept of distinctiveness and thus to lay the methodological foundation permitting to operationalize quantitative procedures in order to use them not only as rough exploratory tools, but in a hermeneutically meaningful way for research in literary studies. Based on a structural definition of potential candidate measures for analyzing distinctiveness in the first section, we offer a systematic description of the issue of integrating quantitative procedures into a hermeneutically meaningful understanding of distinctiveness by distinguishing its epistemological from the methodological perspective. The second section develops a systematic strategy to solve the methodological side of this issue based on a critical reconstruction of the widespread non-integrative strategy in research on keyness measures that can be traced back to Rudolf Carnap's model of explication. We demonstrate that it is, in the first instance, mandatory to gain a comprehensive qualitative understanding of the actual task. We show that Carnap's model of explication suffers from a shortcoming that consists in ignoring the need for a systematic comparison of what he calls the explicatum and the explicandum. Only if there is a method of systematic comparison, the next task, namely that of evaluation can be addressed, which verifies whether the output of a quantitative procedure corresponds to the qualitative expectation that must be clarified in advance. We claim that evaluation is necessary for integrating quantitative procedures to a qualitative understanding of distinctiveness. Our reconstruction shows that both steps are usually skipped in empirical research on keyness measures that are the most important point of reference for the development of a measure of distinctiveness. Evaluation, which in turn requires thorough explication and conceptual clarification, needs to be employed to verify this relation. In the third section we offer a qualitative clarification of the concept of distinctiveness by spanning a three-dimensional conceptual space. This flexible framework takes into account that there is no single and proper concept of distinctiveness but rather a field of possible meanings depending on research interest, theoretical framework, and access to the perceptibility or salience of textual features. Therefore, we shall, instead of stipulating any narrow and strict definition, take into account that each of these aspects – interest, theoretical framework, and access to perceptibility – represents one dimension of the heuristic space of possible uses of the concept of distinctiveness. The fourth section discusses two possible strategies of operationalization and evaluation that we consider to be complementary to the previously provided clarification, and that complete the task of establishing a candidate measure successfully as a measure of distinctiveness in a qualitatively ambitious sense. We demonstrate that two different general strategies are worth considering, depending on the respective notion of distinctiveness and the interest as elaborated in the third section. If the interest is merely taxonomic, classification tasks based on multi-class supervised machine learning are sufficient. If the interest is aesthetic, more complex and intricate evaluation strategies are required, which have to rely on a thorough conceptual clarification of the concept of distinctiveness, in particular on the idea of salience or perceptibility. The challenge here is to correlate perceivable complex features of texts such as plot, theme (aboutness), style, form, or roles and constellation of fictional characters with the unperceived frequency and distribution of word features that are calculated by candidate measures of distinctiveness. Existing research did not clarify, so far, how to correlate such complex features with individual word features. The paper concludes with a general reflection on the possibility of mixed methods research for computational literary studies in terms of explanatory power and exploratory use. As our strategy of combining explication and evaluation shows, integration should be understood as a strategy of combining two different perspectives on the object area: in our evaluation scenarios, that of empirical reader response and that of a specific quantitative procedure. This does not imply that measures of distinctiveness, which proved to reach explanatory power in one qualitative aspect, should be supposed to be successful in all fields of research. As long as evaluation is omitted, candidate measures of distinctiveness lack explanatory power and are limited to exploratory use. In contrast with a skepticism that has sometimes been expressed from literary scholars with regard to the relevance of computational literary studies on proper issues of the humanities, we believe that integrating computational methods into hermeneutic literary studies can be achieved in a way that reaches higher explanatory power than the usual exploratory use of keyness measures, but it can only be achieved individually for concrete tasks and not once and for all based on a general theoretical demonstration. [ABSTRACT FROM AUTHOR]

The present article discusses and reflects on possible ways of operationalizing the terminology of traditional literary studies for use in computational literary studies. By »operationalization«, we mean the development of a method for tracing a (theoretical) term back to text-surface phenomena; this is done explicitly and in a rule-based manner, involving a series of substeps. This procedure is presented in detail using as a concrete example Norbert Altenhofer's »model interpretation« (Modellinterpretation) of Heinrich von Kleist's The Earthquake in Chile. In the process, we develop a multi-stage operation – reflected upon throughout in terms of its epistemological implications – that is based on a rational-hermeneutic reconstruction of Altenhofer's interpretation, which focuses on »mysteriousness« (Rätselhaftigkeit), a concept from everyday language. As we go on to demonstrate, when trying to operationalize this term, one encounters numerous difficulties, which is owing to the fact that Altenhofer's use of it is underspecified in a number of ways. Thus, for instance, and contrary to Altenhofer's suggestion, Kleist's sentences containing »relativizing or perspectivizing phrases such as ›it seemed‹ or ›it was as if‹« (Altenhofer 2007, 45) do by no means, when analyzed linguistically, suggest a questioning or challenge of the events narrated, since the unreal quality of those German sentences only relates to the comparison in the subordinate clause, not to the respective main clause. Another indicator central to Altenhofer's ascription of »mysteriousness« is his concept of a »complete facticity« (lückenlose Faktizität) which »does not seem to leave anything ›open‹« (Altenhofer 2007, 45). Again, the precise designation of what exactly qualifies facticity as »complete« is left open, since Kleist's novella does indeed select for portrayal certain phenomena and actions within the narrated world (and not others). The degree of factuality in Kleist's text may be higher than it is in other texts, but it is by no means »complete«. In the context of Altenhofer's interpretation, »complete facticity« may be taken to mean a narrative mode in which terrible events are reported using conspicuously sober and at times drastic language. Following the critical reconstruction of Altenhofer's use of terminology, the central terms and their relationship to one another are first explicated (in natural language), which already necessitates intensive conceptual work. We do so implementing a hierarchical understanding of the terms discussed: the definition of one term uses other terms which also need to be defined and operationalized. In accordance with the requirements of computational text analysis, this hierarchy of terms should end in »directly measurable« terms – i. e., in terms that can be clearly identified on the surface of the text. This, however, leads to the question of whether (and, if so, on the basis of which theoretical assumptions) the terminology of literary studies may be traced back in this way to text-surface phenomena. Following the pragmatic as well as the theoretical discussion of this complex of questions, we indicate ways by which such definitions may be converted into manual or automatic recognition. In the case of manual recognition, the paradigm of annotation – as established and methodologically reflected in (computational) linguistics – will be useful, and a well-controlled annotation process will help to further clarify the terms in question. The primary goal, however, is to establish a recognition rule by which individuals may intersubjectively and reliably identify instances of the term in question in a given text. While it is true that in applying this method to literary studies, new challenges arise – such as the question of the validity and reliability of the annotations –, these challenges are at present being researched intensively in the field of computational literary studies, which has resulted in a large and growing body of research to draw on. In terms of computer-aided recognition, we examine, by way of example, two distinct approaches: 1) The kind of operationalization which is guided by precedent definitions and annotation rules benefits from the fact that each of its steps is transparent, may be validated and interpreted, and that existing tools from computational linguistics can be integrated into the process. In the scenario used here, these would be tools for recognizing and assigning character speech, for the resolution of coreference and the assessment of events; all of these, in turn, may be based on either machine learning, prescribed rules or dictionaries. 2) In recent years, so-called end-to-end systems have become popular which, with the help of neural networks, »infer« target terms directly from a numerical representation of the data. These systems achieve superior results in many areas. However, their lack of transparency also raises new questions, especially with regard to the interpretation of results. Finally, we discuss options for quality assurance and draw a first conclusion. Since numerous decisions have to be made in the course of operationalization, and these, in practice, are often pragmatically justified, the question quickly arises as to how »good« a given operationalization actually is. And since the tools borrowed from computational linguistics (especially the so-called inter-annotator agreement) can only partially be transferred to computational literary studies and, moreover, objective standards for the quality of a given implementation will be difficult to find, it ultimately falls to the community of researchers and scholars to decide, based on their research standards, which operationalizations they accept. At the same time, operationalization is the central link between the computer sciences and literary studies, as well as being a necessary component for a large part of the research done in computational literary studies. The advantage of a conscious, deliberate and reflective operationalization practice lies not only in the fact that it can be used to achieve reliable quantitative results (or that a certain lack of reliability at least is a known factor); it also lies in its facilitation of interdisciplinary cooperation: in the course of operationalization, concrete sets of data are discussed, as are the methods for analysing them, which taken together minimizes the risk of misunderstandings, »false friends« and of an unproductive exchange more generally. [ABSTRACT FROM AUTHOR]

The present study proposes an experimental exploration of the Romanian novel written between 1920 and 1940 through the use of stylometry, a method of distant reading employed for the statistical analysis of style. Drawing from the most recent advances in the field of computational stylistics, we select a formal standpoint from which we seek to investigate the relation between the Romanian novelistic canon and minor, tertiary novels published in the same. In our test cases, we will attempt to establish some of the more promising aspects of stylometric analysis, as well as single out the experiments that yield no relevant result. Because of the relative novelty of the method, the purpose of our investigations is to offer a kind of pilot experiment that can illustrate the benefits of using computational methods on Romanian literary corpora. [ABSTRACT FROM AUTHOR]