Search

The paper verifies the efficiency of stylometric methods for short texts when considering different numbers of candidate authors. Analyses are run on corpora in four different languages using multiple methods. Final outcome is an overview of estimated efficiency scores which may be used as guidelines for authorship attribution studies.

The paper adopts the impostors method to verify if the real identity of the German author B. Traven corresponds to that of Ret Marut. The approach is fine tuned and applied to four novels by the two authors. Results suggest that they are probably written by the same person.

1. Premessa metodologica: operazionalizzare la risposta del lettore Gli ultimi decenni negli studi letterari sono stati segnati da un crescente interesse per fenomeni tanto stimolanti quanto problematici come l’empatia negativa e l’immoralità del personaggio. Gli studi dedicati a questi soggetti sembrano rispondere a un’esigenza comune, che scaturisce dalle più recenti evoluzioni nel panorama internazionale (e intermediale) delle produzioni narrative e che si riflette nelle somiglianze tra le...

La celebre battuta di Gide che apre questo volume si propone di indagare il complesso rapporto fra etica, estetica e rappresentazione, ma riformulando l’aforisma in forma interrogativa: “Con i buoni sentimenti si fanno brutti libri?”. È proprio così? È ancora così? Ma è, in fin dei conti, davvero sempre stato così? Cercare di rispondere a questa domanda vuol dire riflettere non solo sul valore estetico delle opere, ma anche sulla liceità o sulla pericolosità delle rappresentazioni; significa chiedersi se la cosa di cui si parla conta e qual è il significato etico del come è condotta la rappresentazione, è organizzata la forma; significa anche riflettere su alcune complesse problematiche che sempre più spesso sono al centro dei dibattiti contemporanei: la relazione fra autorialità e opera, fra scrittura e mercato, il canone, la visibilità, il ruolo pedagogico della letteratura, la funzione delle istituzioni, della censura fino ai dibattiti sulla cancel culture, sul politicamente corretto, sulla cultura woke, sull’appropriazione culturale, su un certo moralismo di ritorno, sul ruolo ideologicamente orientato del culturalismo, le relazioni fra la voce letteraria di una soggettività subalterna e i criteri di attribuzione del valore estetico.

"This poster reports on the groundwork for the computational study of evaluative practices in German language book reviews. We trained classifiers for evaluation and sentiment at sentence level on the LOBO corpus, comprising ~1.3 million book reviews downloaded from the social reading platform LovelyBooks. For the two classification tasks, we compared performance of dictionary-based and transfer-learning (TL) based sentiment analysis (SA). Our results highlight the higher efficiency of TL-methods and of dictionaries based on vector space models (like SentiArt and AffectiveNorms). They show that computational methods can reliably identify sentiment of book reviews in German. " Ein Beitrag zur 8. Tagung des Verbands "Digital Humanities im deutschsprachigen Raum" - DHd 2022 Kulturen des digitalen Gedächtnisses.

The Social Web is a network of people and platforms, of performances and products; of reactions, opinions, judgments, and comparisons; of emotions, valuations, and affects; of evaluations, ratings, and rankings. Shared and connective practices lead to emergent, fluid, and sometimes quite stable, cultures of valuation and evaluation, managing issues of identity, world view, and social participation. In the late fall of 2020, the conference Digital Practices,1 virtually held in Basel (CH), asked about such cultures and issues, focusing on practices of reading, writing, and evaluation on the social web. Following up on that conversation, and zooming in on evaluation practices, we are glad to now introduce a special issue of the Journal of Cultural Analytics entitled “Cultures of evaluation on the social web”.

With the development of new powerful technologies for computational data analysis, the opportunities for -- and interest in -- the detection of sentiments and opinion in texts have grown considerably (Liu 2015). Because of the vast amount of material available online, these investigations have focused mostly on textual material gathered from social media, making use of traditional corpus linguistic approaches as well as deep learning tools. Sophisticated sentiment analysis (SA) of literary texts, especially in languages other than English, is still in its infancy (Kim and Klinger 2019). This has depended partly on the limited amount of digital texts available, partly the complex structure of literary texts, and finally on methodological challenges, with skills needed that seldom form part of the training of literary scholars. Emotions are however central to the experience of literary narrative (Oatley 2012; Hogan 2016), and recent advances in their systematic, quantitative analysis have been made within computational literary studies. Yet, such investigations have mostly relied on existing lists of words associated with sentiment and emotion values, the so-called sentiment lexicons. While these remain conventional and useful tools, they can only provide limited insights to the representation of emotions in texts. Using a lexicon-based method, we have previously investigated emotions and sentiments in relation to the representation of landscape in Swiss literature, looking in particular at the differences between the rural and urban spaces portrayed in a corpus of Swiss novels written in German (see Grisot, G., Herrmann, J.B. (in preparation). The present paper takes a step forward, using manual annotation and advanced machine learning methods to train a fine-tuned model to recognise valence and arousal on a historical corpus. Our goals are higher levels of lexical coverage and validity when compared to our prior results obtained with sentiment lexicons. We describe here the current state of our method to detect sentiment using deep learning approaches. Using a language model trained on a large corpus (3000+) of German literary texts spanning from 1800 to 1950 (Fischer and Strötgen 2017), we make use of BERT word embeddings and manually annotated sentences to recognise sentiment. 500+ sentences were taken from three Swiss-German novels - one of which children's fiction - and annotated for valence - understood here as the degree of 'positivity' of the detected sentiment - and arousal - its 'intensity' or 'degree of activation' - by two trained student assistants using the same instructions. Currently, intra-class correlation coefficient (ICC) between manual annotators calculated on these sentences is 0.721 for valence and 0.606 for arousal. Scores for individual texts indicated preliminary evidence of a genre effect, with higher ICCs for the children's novel (valence 0.86; arousal 0.78 for 149 sentences) as compared to the other two, more complex, realist novels (valence 0.78, 0.62 arousal for 182 sentences; 0.51 for valence, 0.41 arousal for 198 sentences). The annotated sample was used to train a deep learning classifier, using linear regression to finetune the Literary German BERT model (https://huggingface.co/severinsimmler/literary-german-bert), which reached Pearson's r scores of 0.53 for valence and 0.63 for arousal. These scores are very promising, suggesting the possibility - provided more training data - of a full automation of the annotation task on our domain of historical literary texts. We are currently appending the annotation and at the time of the conference shall be able to update the results on a broader data base. While potentially taking automatic SA of German literary texts to a new level, our study also allows evaluating the performance of lexicon-based in direct comparison with deep learning SA approaches, thus allowing to gauge the validity of different SA methods on a data-driven basis. This approach also raises questions concerning the effect of genre on the ease and validity of manual sentiment annotations.

We present our method and interim results of the “Mining Goodreads” project, aimed at developing a computational approach to measure reading absorption in user-generated book reviews in English. A team of eight people (three supervisors and five annotators) have joined skills from the fields of empirical literary studies, natural language processing, and digital humanities, with the goal of producing a gold-standard annotated dataset and strengthening the theoretical framework of reading absorption. Annotation of more than 800 texts showed the difficulties in finding an agreement in the tagging of sentences. However, through more than one year of work in strict collaboration, the team reached some substantial improvements: inter-annotator agreement increased through seven annotation rounds, while machine learning approaches were applied on the annotated corpus, producing promising results.

International audience; The end of deep reading is a commonplace in public debates, whenever societies talk about youth, books, and the digital age. In contrast to this, we show for the first time and in detail, how intensively young readers write and comment literary texts at an unprecedented scale. We present several analyses of how fiction is transmitted through the social reading platform Wattpad, one of the largest platforms for user-generated stories, including novels, fanfiction, humour, classics, and poetry. By mixed quantitative and qualitative methods and scalable reading we scrutinise texts and comments on Wattpad, what themes are preferred in 13 languages, what role does genre play for readers behaviour, and what kind of emotional engagement is prevalent when young readers share stories. Our results point out the rise of a global reading culture in youth reading besides national preferences for certain topics and genres, patterns of reading engagement, aesthetic values and social interaction. When reading Teen Fiction social-bonding (affective interaction) is prevalent, when reading Classics social-cognitive interaction (collective intelligence) is prevalent. An educational outcome suggests that readers who engage in Teen Fiction learn to read Classics and to judge books not only in direct emotional response to character’s behaviour, but focusing more on contextualised interpretation of the text.

Le congrès ne s'est pas tenu physiquement aux dates et lieu prévus mais les proceedings ont été publiés et diffusés en ligne.; International audience; To detect how and when readers are experiencing engagement with a literary work, we bring together empirical literary studies andlanguage technology via focusing on the affective state of absorption. The goal of our resource development is to enable the detectionof different levels of reading absorption in millions of user-generated reviews hosted on social reading platforms. We present a corpusof social book reviews in English that we annotated with reading absorption categories. Based on these data, we performed supervised,sentence level, binary classification of the explicit presence vs. absence of the mental state of absorption. We compared the performancesof classical machine learners where features comprised sentence representations obtained from a pretrained embedding model (UniversalSentence Encoder) vs. neural classifiers in which sentence embedding vector representations are adapted or fine-tuned while trainingfor the absorption recognition task. We discuss the challenges in creating the labeled data as well as the possibilities for releasing a benchmark corpus.

Books but also movies, TV-series, fanfictions, role-playing games, and much more. The fantasy narrative genre shows one of the highest levels of transmediality. This paper proposes an explanation of the phenomenon, combining the worldbuilding theory with three different approaches in the field of cognitive science. Referring to Gallese’s embodied simulation, the transportation in the Tolkienian “Secondary Worlds” invites a progressive refinement of the fictional universe, allowing multiple media to support its configuration—while also improving personal cognitive skills. In terms of Clark’s extended mind, then, the peculiar involvement stimulated by this type of creations incites a proactive approach to the reading experience, widening it through different tools—while also saturating the possible extensions of the imaginative space. At the same time, these processes can induce insidious addictive dynamics (usually related to the subject’s proneness to excessive daydreaming, but also to the general characteristics of children’s imagination), reinforced by marketing strategies which multiply the cognitive approaches. The theoretical discourse will be supported by narratological analyses of best-seller fantasy novels such as those by Rowling, Martin and Meyer. Some empirical testing will be provided by readers’ reviews on the Goodreads web community, confirming a possible connection between transmediality, narrative transportation and addiction in fantasy fiction.

A single abstract from the DHd-2018 Book of Abstracts., Sofern eine editorische Arbeit an dieser Publikation stattgefunden hat, dann bestand diese aus der Eliminierung von Bindestrichen in Überschriften, die aufgrund fehlerhafter Silbentrennung entstanden sind, der Vereinheitlichung von Namen der Autor*innen in das Schema "Nachname, Vorname" und/oder der Trennung von Überschrift und Unterüberschrift durch die Setzung eines Punktes, sofern notwendig., {"references":["https://doi.org/10.5281/zenodo.3684897","https://github.com/DHd-Verband/DHd-Abstracts-2018"]}