Search

This paper presents a general-purpose NLP pipeline that achieves state-of-the-art performance on the Ancient Greek Perseus UD Treebank for several tasks (POS Tagging, Morphological Analysis and Dependency Parsing), and close to state-of-the-art performance on the Proiel UD Treebank. Our aim is to provide a reproducible, open source language processing pipeline for Ancient Greek, capable of handling input texts of varying quality. We measure the performance of our model against other comparable tools and then evaluate lemmatization errors.

The way in which Chinese diplomats communicate has changed recently,from being mostly reactive and pragmatic to being rhetorically more combative.This has generated strong academic, media, and policy interest.However, less academic attention has been devoted to the employmentof social media for China’s new diplomatic communication strategy. Byanalyzing the recent employment of Twitter by China’s Ministry of ForeignAffairs (MFA), this article explores the initial digitalization of China’s publicdiplomacy from November 2019 to February 2021. Approaching Twitter asboth a virtual network structure and an interactive strategic communicationprocess, we collected 61,000 tweets from Chinese diplomats plus 282,000tweets from Chinese official media and applied data analytics to examinehow the MFA augmented its diplomatic digital presence by responding,reposting/retweeting, mentioning, and hashtagging. We also used discourseanalysis to investigate how Chinese diplomats selected topics togenerate, diffuse, and affect hegemonic discourses. We argue that China’sMFA initially adopted Twitter using a centrally controlled structure of topic,rhetoric, and discourses as well as cohesive dissemination and augmentingstrategies. These communication structures created a self-referencing networkclosely aligned with Chinese official media on Twitter.

This article explores the sentiment dynamics present in narratives and their contribution to literary appreciation. Specifically, we investigate whether a certain type of sentiment development in a literary narrative correlates with its quality as perceived by a large number of readers. While we do not expect a story's sentiment arc to relate directly to readers' appreciation, we focus on its internal coherence as measured by its sentiment arc's level of fractality as a potential predictor of literary quality. To measure the arcs' fractality we use the Hurst exponent, a popular measure of fractal patterns that reflects the predictability or self-similarity of a time series. We apply this measure to the fairy tales of H.C. Andersen, using GoodReads' scores to approximate their level of appreciation. Based on our results we suggest that there might be an optimal balance between predictability and surprise in a sentiment arcs' structure that contributes to the perceived quality of a narrative text.

Narrative organization of information ties together storytelling in its many modalities. One archetypal expression of narratives we find in literary fiction. In this paper, we approach the elements of a successful narrative, and by extension storytelling, from the perspective of computational narratology. We are specifically interested in how to identify 'a good story'. Quality assessment of literature is complicated by many factors. Literature is a complex linguistic phenomenon that conveys information indirectly, readers have different aesthetic preferences, and there is a lack of proper scientific instruments. One noisy, but ecologically valid measure is quantitative 'reader reviews.' On this account, a narrative is successful if readers rate it high. Such an 'extrinsic' success criterion is tempting because it is relatively easy to access, reflects readers' preferences in a natural setting, and its standardization appears trivial. A criterion that relies on reviews is however prone to several well-known biases, for instance, gender [1], ethnicity, and race [2], which point to fairness challenges in the classification of real-world data [3]. Instead of merely relying of review annotation of the success of a story, we suggest paying attention to the inner structure of a story, termed the 'intrinsic success'. A recent theoretical paper has suggested that the affective coherence of a story, that is, the self-similarity of a sentiment story arc, functions as an index of a narrative's intrinsic success [4]. A complementary empirical study has shown that affective coherence can detect canonical literature [5]. (something is missing here) While the use of computational narratology may seem compelling to minimize demographic disparities introduced by extrinsic success, it introduces less apparent and unknown biases. Genre, for instance, impacts a story arc and shows complex interactions with psychological propensities, aesthetic evaluation, and gender [1]. Socio-cultural norms may also play an important role in introducing unknown biases even at the methodological level. In sum, there is no golden path to successful storytelling, that is, no single path that optimizes both quality and bias response. Instead, we see a multitude of possible trajectories, each of which implies different choices of known and unknown biases. References [1] S. Touileb, L. Øvrelid, E. Velldal, Gender and sentiment, critics and authors: a dataset ofNorwegian book reviews, in: Proceedings of the Second Workshop on Gender Bias inNatural Language Processing, Association for Computational Linguistics, Barcelona, Spain(Online), 2020, pp. 125-138. [2] P. Chong, Reading difference: How race and ethnicity function as tools for critical appraisal, Poetics 39 (2011) 64-84. [3] T. Miconi, The impossibility of "fairness": a generalized impossibility result for decisions,2017.arXiv:1707.01195. [4] Q. Hu, B. Liu, M. R. Thomsen, J. Gao, K. L. Nielbo, Dynamic evolution of sentiments in Never Let Me Go: Insights from multifractal theory and its implications for literary analysis,Digital Scholarship in the Humanities 36 (2020) 322-332. [5] Y. Bizzoni, T. Peura, M. R. Thomsen, K. L. Nielbo, Sentiment Dynamics of Success: Fractal Scaling of Story Arcs Predicts Reader Preferences, 2021. Proceedings of the First Workshop on Natural Language Processing for Digital Humanities (2021), 1-6.

In a classic study of Nuer religion, British Social Anthropologist E.E. Ev-ans-Pritchard explored the problem of religious symbols embedded in the Nuer metaphor ‘twins are birds’. In this paper we present a study conclud-ing that not twins but mermaids are birds. At least this is how they seman-tically behave in the lexical habitat of the influential Danish romanticist and nineteenth-century poet, pastor, and politician N.F.S. Grundtvig (1783-1872). As in the Nuer case the cause for this behavior is to be found in the symbolic structures of a religious logic. The study consists of word embed-dings plotting the bestiary arising from Grundtvig’s 1068 publications in their tokenized, lemmatized, ‘algorithmifyed’ avatar. Our interest here lies with exploring how non-human animals are displayed in a material that have left a dual cultural and religious imprint in Denmark. Anticipating the conclusion: pigs are food; mermaids are birds.

Entertainment is important. Stories and narration are constants in, if not a prerequisite for, human culture. Running on myths and their recitation in ritual settings, religions hinge on this fact. Nevertheless, this is a circumstance that has been sought glossed over within certain religious traditions dominated by intellectual guilds. Not least within specific Christian traditions. Christianity’s manyfold Protestant variations are, for instance, characterized by an intellectual proclivity for hermeneutically complex and challenging theories, while suppressing straightforwardly enjoyable stories. This proclivity could, further, be said to have fueled a so-called ‘disenchantment’ impetus imbued in processes going by the names of ‘secularization’ and ‘rationalization’. Such terms seek to catch the deep-rooted tendency among changing Christian clerisies to adapt to a naturalist worldview at the expense of stories about the fantastic. That is to say that myriads of theologians, pastors, and poets throughout history have aspired to prune and ‘demythologize’ the core Christian narratives. Though this trend is deep-rooted, it broadened and accelerated remarkably in Europe through the course of the eighteenth century.But, seemingly, stories and storytelling will out. The rise of the narratively enthusiastic Romantic Movement appears to have run on this hydraulic logic. Affected by this current, the highly influential Danish poet, pastor, and politician N.F.S. Grundtvig (1783-1872) re-enchanted Danish Christianity. At least he aimed to re-introduce an appreciation of wonder and storytelling – of an oral, narrative, fantastical culture – within Danish church life. The manifold fantastic beasts roaming his works are the residue of this aspiration. Word embeddings of these creatures tell the tale of a man laboring to reintegrate agency, plotlines, and narrative engagement into Christianity.This study combines simple neural embeddings and graph theory to represent the bestiary arising from Grundtvig’s 1073 publications in their tokenized, lemmatized, ‘algorithmifyed’ avatar. It is based on the digital scholarly edition Grundtvig’s Works. We have computed the distance between a set of so-called seed terms and the corpus lexicon. The catalogue of seed terms have been established following the 2538 entries of the so-called Mythological Register developed by Grundtvig’s Works. For each seed, the algorithm excerpted a pre-set number of primary associations of size m. These are the terms with the shortest distance to the seed term. For each of the m-terms the algorithm, furthermore, extracted a pre-set number of secondary associations. The next step was to compute the distance between these respective categories of terms; subsequently they were connected based on their distance under a threshold estimated from the distance variance structure. At the final stage, semantic clusters were unearthed by way of the Louvain method. These clusters are ripe with verbs, agents, and places whispering of glorious deeds and enchanting tales: of a revival of storytelling.

Narrative organization of information ties together storytelling in its many modalities. One archetypal expression of narratives we find in literary fiction. In this paper, we approach the elements of a successful narrative, and by extension storytelling, from the perspective of computational narratology. We are specifically interested in how to identify ’a good story’ and navigate in two dimensions of literary success: ‘Extrinsic’ and ‘intrinsic’. We investigate the association between the self-similarity of a sentiment story arc and review assessment of a literary work. In doing so, we direct our attention to known and unknown biases in the suggested dimensions of success to avoid reinforcing existing unwanted structures in our exploration of successful narratives.Quality assessment of literature is not a simple inquiry and is complicated by various factors. Literature is a complex linguistic phenomenon that conveys information indirectly, and readers have different aesthetic preferences, and, in general, there is a lack of robust scientific instruments for measuring literary quality. One noisy, but ecologically valid measure is quantitative ’reader reviews.’ On this account, a narrative is successful if readers rate it high. Such an ’extrinsic’ success criterion is tempting because it is relatively easy to access, reflects readers’ preferences in a natural setting, and its standardization appears trivial. A criterion that relies on reviews is however prone to several well-known biases, for instance, grading disparities between gender [1], ethnicity and race [2], which point to fairness challenges in classification of real-world data [3]. Instead of merely relying upon review annotation of the success of a story, we suggest paying attention to the inner structure of a story, the ’intrinsic success’.A recent theoretical paper has suggested that the affective coherence of a story, that is, the self-similarity of a sentiment story arc, functions as an index of a narrative’s intrinsic success [4]. A complementary empirical study has shown that affective coherence can detect canonical literature [5].While the use of computational narratology may seem compelling to minimize demographic disparities introduced by extrinsic success, it introduces less apparent and unknown biases. Genre, for instance, impacts a story arc and shows complex interactions with psychological propensities, aesthetic evaluation, and gender [1]. In this work, we examine the association between the internal sentiment structure of a work and known biases. Socio-cultural norms may also play an important role in introducing unknown biases even at the methodological level, such as representational biases of reader types.In sum, there is no golden path to identify successful storytelling, that is, no single path that optimizes both quality assessment and bias response. Instead of relying on single dimensions of success, either compelling computational approaches or accessible standardization, we suggest a deliberate combination of dimensions and approaches which includes choices about bias acceptance. We see a multitude of possible trajectories, each of which implies different choices of known and unknown biases.

Natural Language Processing methods hold promise for improving clinical prediction by utilising information otherwise hidden in the clinical notes of electronic health records. However, clinical practice—as well as the systems and databases in which clinical notes are recorded and stored—change over time. As a consequence, the content of clinical notes may also change over time, which could degrade the performance of prediction models. Despite its importance, the stability of clinical notes over time has rarely been tested. Therefore, in this study, we examined the lexical stability of clinical notes from the Psychiatric Services of the Central Denmark Region in the period from January 1, 2011, to November 22, 2021 (a total of 14,811,551 clinical notes describing 129,570 patients) by quantifying sentence length, readability, syntactic complexity and clinical content - and estimating changepoints in these metrics. We find lexical and syntactic stability over time, which bodes well for the use of Natural Language Processing for predictive modelling in clinical practice.

This article relies on information-theoretic measures to examine how events impacted the news for the period 1950-1995. Moreover, we present a method for event characterization in (unstructured) textual sources, offering a taxonomy of events based on the different ways they impacted the flow of news information. The results give us a better understanding of the relationship between events andtheir impact on news sources with varying ideological backgrounds.

Undertaking a distant reading of exclamation marks in the digitized and an-notated N.F.S. Grundtvig data, this paper targets a trait of an overall roman-ticist emotionalizing trend in a corpus of 19th century literature: It proposes to analyze the use of exclamation marks as a deposition of heightened atten-tion to emotional experience and intention in printed matter and typeset-ting in the writings of the Danish poet, priest and politician N.F.S. Grundtvig (1783-1872), who is widely regarded as the central figure in the 19th century Danish religious development and cultural nation building process. As such this paper sketches the temporal as well as semantic con-texts of the exclamation marks.

Danish natural language processing (NLP) has in recent years obtained considerable improvements with the addition of multiple new datasets and models. However, at present, there is no coherent framework for applying state-of-the-art models for Danish. We present DaCy: a unified framework for Danish NLP built on SpaCy. DaCy uses efficient multitask models which obtain state-of-the-art performance on named entity recognition, part-of-speech tagging, and dependency parsing. DaCy contains tools for easy integration of existing models such as for polarity, emotion, or subjectivity detection. In addition, we conduct a series of tests for biases and robustness of Danish NLP pipelines through augmentation of the test set of DaNE. DaCy large compares favorably and is especially robust to long input lengths and spelling variations and errors. All models except DaCy large display significant biases related to ethnicity while only Polyglot shows a significant gender bias. We argue that for languages with limited benchmark sets, data augmentation can be particularly useful for obtaining more realistic and fine-grained performance estimates. We provide a series of augmenters as a first step towards a more thorough evaluation of language models for low and medium resource languages and encourage further development.

During the first wave of Covid-19 information decoupling could be observed in the flow of news media content. The corollary of the content alignment within and between news sources experienced by readers (i.e., all news transformed into Corona-news), was that the novelty of news content went down as media focused monotonically on the pandemic event. This all-important Covid-19 news theme turned out to be quite persistent as the pandemic continued, resulting in the, from a news media's perspective, paradoxical situation where the same news was repeated over and over. This information phenomenon, where novelty decreases and persistence increases, has previously been used to track change in news media, but in this study we specifically test the claim that new information decoupling behavior of media can be used to reliably detect change in news media content originating in a negative event, using a Bayesian approach to change point detection.

The COVID-19 pandemic has been shown to have a major negative impact on global mental health and patients with mental illness may be particularly vulnerable. We show that developments in COVID-19 pandemic-related psychopathology among patients with mental illness can be meaningfully monitored using machine learning methods. The COVID-19 pandemic-related psychopathology was found to covary with the pandemic pressure. This correlation was, however, less pronounced during the second wave compared to the first wave of the pandemic - possibly due to habituation.

Undertaking a distant reading of letter-spacings in the digitized andannotated N.F.S. Grundtvig data, this paper targets a trait of an overall romanticistemotionalizing trend in a corpus of 19th century literature: It proposes to analyzethe letter-spacings as a deposition of heightened attention to subjectiveemotional experience in printed matter and typesetting in the writings of the Danishpoet, priest and politician N.F.S. Grundtvig (1783-1872), who is widely regardedas the central figure in the 19th century Danish religious development andnation building process. As such this paper sketches the temporal and semanticcontexts of the letter-spacings.

Undertaking a distant readingofletter-spacings in the digitized and annotated N.F.S. Grundtvigdata, this paper targets a trait of an overall romanti-cist emotionalizingtrend in a corpus of 19thcentury literature: It proposes to an-alyze the letter-spacings as a deposition of heightened attention to subjective emotional experience in printed matterand typesetting in the writings of the Dan-ish poet, priest and politician N.F.S. Grundtvig (1783–1872), who is widely re-garded as the central figure in the 19thcentury Danishreligious development andnation buildingprocess. As such this paper sketches the temporal and semantic contexts of the letter-spacings

Historians have regularly debated whether advertisements can be used as a viable source to study the past. Their main concern centered on the question of agency. Were advertisements a reflection of historical events and societal debates, or were ad makers instrumental in shaping society and the ways people interacted with consumer goods? Using techniques from econometrics (Granger causality test) and complexity science (Adaptive Fractal Analysis), this paper analyzes to what extent advertisements shaped or reflected society. We found evidence that indicate a fundamental difference between the dynamic behavior of word use in articles and advertisements published in a century of Dutch newspapers. Articles exhibit persistent trends that are likely to be reflective of communicative memory. Contrary to this, advertisements have a more irregular behavior characterized by short bursts and fast decay, which, in part, mirrors the dynamic through which advertisers introduced terms into public discourse. On the issue of whether advertisements shaped or reflected society, we found particular product types that seemed to be collectively driven by a causality going from advertisements to articles. Generally, we found support for a complex interaction pattern dubbed the consumption junction. Finally, we discovered noteworthy patterns in terms of causality and long-range dependencies for specific product groups. All in, this study shows how methods from econometrics and complexity science can be applied to humanities data to improve our understanding of complex cultural-historical phenomena such as the role of advertising in society.

In the history of prolific authors, we are confronted with the figure of the suffering author. Setting aside metaphysical theories, the central claim seems to be that a state incongruent dynamic is an intricate part of the creativity process. Two propositions can be derived this claim, 1: the creative state is inversely proportional to the emotional state, and 2: the creative state is causally predicted by the emotional state. We call this creative emotional dynamic `The Dostoyevskian Trope'. In this paper we present a method for studying the Dostoyevskian trope in prolific authors. The method combines Shannon entropy as an indicator of lexical variability with fractal analysis in order to measure creative dynamics over multiple documents. We generate a sentiment time series from the same documents and test for asymmetric directed dependencies between the creative and sentiment time series. We illustrate the method by searching for the Dostoyevskian trope in Danish textual cultural heritage, specifically three highly prolific authors from the 19th century, namely, N.F.S. Grundtvig, H.C. Andersen, and S.A. Kierkegaard.