What happens when we track Shakespeare’s language using computers and large-scale databases like EEBO-TCP? In this study, we begin with a question from a computer scientist (what’s Shakespeare’s ‘favourite’ word?), and follow it through to a consideration of Shakespeare’s reading and influences, and evidence and uncertainty in quantitative literary analysis. We are used to looking for words Shakespeare might have invented, but what about those he picked up from other writers? Might they not be more interesting in terms of understanding how his imagination worked? We identify one such word – ‘sequent’ – which no other major dramatist uses, but which Shakespeare returns to, in different grammatical roles, and with different stylistic resonances, nine times – and of which he becomes especially fond in the years 1600–1605. Our aim is to highlight the history of a single word, and track its passage through print generally, and specifically in Shakespeare, but also to demonstrate the richness digital tools and methods can bring to traditional reading.

The layperson’s seemingly automatic reaction to Shakespeare’s language is to comment on the huge number of words he apparently created. Only relatively recently have scholars been attempting to establish the truth of this. Jonathan Hope has examined sixteen words (“gloomy”, “eyeball”, “manager”, etc.) claimed to be Shakespeare neologisms, and shows that none stand up to scrutiny – all can be antedated. However, how exactly other early modern playwrights were using affixes – the prefixes and suffixes that build words – is not well known. Perhaps the penchant applied more generally to the playwrights of that period. This chapter examines Shakespeare’s affixes, their frequencies and patterns of use, and, importantly, how they compare with those of his contemporaries. All this is made possible by the Enhanced Shakespearean Corpus, a richly annotated set of corpora built for the analysis and comparison of Shakespeare’s language by the Encyclopaedia of Shakespeare’s Language Project (http://wp.lancs.ac.uk/shakespearelang/).

This chapter combines digital search tools with traditional philological methods to explore Shakespeare’s use of the linguistic repertoires embodied in the Book of Common Prayer and English translations of the Bible. On a daily, weekly, and yearly basis, Shakespeare (not to mention his readers and playgoing audience) heard and repeated the regimen of biblical quotations, prayers, and theological propositions encoded in the Book of Common Prayer. These repetitions made available a kind of embodied dictionary of formal categories and templates. Shakespeare’s plays and poems make extensive use of that dictionary. When Shakespeare filled these forms, he did so by selecting words and fitting them to the form in sometimes surprising ways. This chapter argues that the dramatic and poetic power of Shakespeare’s language derives from this filling of words with forms. Indeed, many of Shakespeare’s uses of forms from the Book of Common Prayer or the Bible carry with them what we call content or semantic features, so that our experience of Shakespeare’s language is in fact a register of Shakespeare’s experience of the language of the Bible.

Recent advances in data-driven behavioural science and, particularly, in Behavioural Data Science, saw the rise of applying natural language processing techniques to understanding and modelling human behaviour, algorithmic behaviour, as well as behaviour of complex human–machine systems. From associative modelling in the standard psychological experiments to understanding emotional arcs in novels and movies through the way humans, algorithms and complex systems use language, this chapter demonstrates how computational linguistics methods allow behavioural methodology to go beyond the ‘sterile’ laboratory environments into the field using data, test hypotheses at scale and have scalable practical impact. This chapter also shows how language-based modelling can shed light on cognition, decision-making, judgements and cultural evolution. Using empirical example of a large-scale Behavioural Data Science study, this chapter also demonstrates how language analysis can be used as a ‘truth serum’, helping to obtain underlying human preferences from subjective judgements usually provided in surveys.

Chapter 7 discusses how language and computer use interact and some of the problems that can occur when relying on natural language processing and machine learning. We discuss some of the benefits and challenges of automatic parsing, how algorithms are applied and can alter what gets shown in searches, and more. We provide several examples of AI generation gone wrong and encourage caution when using large language models, but also how knowledge about linguistics and how language works can inform our own use of language-based technology.

Distributional approaches following the Firthian principle have revolutionized linguistics. While Firthian approaches in collocation research detect syntagmatic relations and are a key research area in corpus linguistics, Firthian distributional semantics and their neural counterpart of word embeddings detect paradigmatic relations and have fundamentally impacted computational linguistics. We combine these two closely related approaches: our hypothesis, following Ricoeur’s view of a metaphor as a clash of two normally distinct semantic fields, is that idioms are collocations in which the lexical participants typically have low semantic similarity in the word embedding space, i.e. low values for the cosine metric. We test if the cosine metric, replaceability with synonyms, and linear combinations with collocation measures improve idiom detection for three constructions: verb-PP, light verbs, and compound nouns. We report improved idiom detection by 10 to 80 per cent, and almost half of compound noun non-compositionality is predicted by cosine alone. We trace how compound nouns are changing in spoken and written English, mirroring digitalisation and the revolution of the internet.

Advances in natural language processing (NLP) and Big Data techniques have allowed us to learn about the human mind through one of its richest outputs – language. In this chapter, we introduce the field of computational linguistics and go through examples of how to find natural language and how to interpret the complexities that are present within it. The chapter discusses the major state-of-the-art methods being applied in NLP and how they can be applied to psychological questions, including statistical learning, N-gram models, word embedding models, large language models, topic modeling, and sentiment analysis. The chapter concludes with ethical discussions on the proliferation of chat “bots” that pervade our social networks, and the importance of balanced training sets for NLP models.

Framenets and constructiCons are applied instantiations of the linguistic frameworks known as Frame Semantics and Construction Grammar, respectively, in the form of computational, semiformally structured linguistic resources. The resources have a common history, both theoretically and in design: They are built as English-language resources in the framework of the Berkeley FrameNet initiative. They enjoy the double nature of being descriptive linguistic resources as well as finding frequent use in a computational linguistic context, where they have been used both in NLP applications and as underlying knowledge bases in areas such as computer-assisted language learning. The chapter provides a bird’s-eye view on these resources: their theoretical foundations; design principles and how they are compiled; theoretical and methodological interrelations; the challenges involved in building framenets and constructiCons for new languages and for cross-linguistic application; the differences and interactions between linguistic and computational linguistic work on framenets and constructiCons; application to language pedagogy; and outstanding theoretical and methodological issues.

Language is the natural currency of most social communication. Until the emergence of more powerful computational methods, it simply was not feasible to measure its use in mainline social psychology. We now know that language can reveal behavioral evidence of mental states and personality traits, as well as clues to the future behavior of individuals and groups. In this chapter, we first review the history of language research in social personality psychology. We then survey the main methods for deriving psychological insights from language (ranging from data-driven to theory-driven, naturalistic to experimental, qualitative to quantitative, holistic to granular, and transparent to opaque) and describe illustrative examples of findings from each approach. Finally, we present our view of the new capabilities, real-world applications, and ethical and psychometric quagmires on the horizon as language research continues to evolve in the future.

This chapter surveys the history and main directions of natural language processing research in general, and for Slavic languages in particular. The field has grown enormously since its beginning. Especially since 2010, the amount of digital texts has been rapidly growing; furthermore, research has yielded an ever-greater number of highly usable applications. This is reflected in the increasing number and attendance of NLP conferences and workshops. Slavic countries are no exception; several have been organising international conferences for decades, and their proceedings are the best place to find publications on Slavic NLP research. The general trend of the evolution of NLP is difficult to predict. It is certain that deep learning, including various new types (e.g. contextual, multilingual) of word embeddings and similar ‘deep’ models will play an increasing role, while predictions also mention the increasing importance of the Universal Dependencies framework and treebanks and research into the theory, not only the practice, of deep learning, coupled with attempts at achieving better explainability of the resulting models.

The introduction to this volume describes its content. It also provides the rationale for including selected topics and provides comments on the manner of presentation adopted in this volume.

In this chapter, a case is made for the inclusion of computational approaches to linguistics within the theoretical fold. Computational models aimed at application are a special case of predictive models. The status quo in the philosophy of linguistics is that explanation is scientifically prior to prediction. This is a mistake. Once corrected, the theoretical place of prediction is restored and, with it, computational models of language. The chapter first describes the history behind the emergence of explanation over prediction views in the general philosophy of science. It’s then suggested that this post-positivist intellectual milieu influenced the rejection of computational linguistics in the philosophy of theoretical linguistics. A case study of the predictive power already embedded in contemporary linguistic theory is presented through some work on negative polarity items. The discussion moves to the competence–performance divide informed by the so-called Galilean style in linguistics that retains the explanatory over prediction ideal. In the final sections of the chapter, continuous methods, such as probabilistic linguistics, are used to showcase the explanatory and predictive possibilities of nondiscrete approaches, before a discussion of the contemporary field of deep learning in natural language processing (NLP), where these predictive possibilities are further amplified.