This chapter examines distributed semantics and language models, Word2Vec and BERT, for obtaining word and sentence embeddings to extract knowledge representations from naturalistic stimuli in behavioural data science applications. These representations enable large-scale study of human cognition and behaviour, providing insights into higher-level psychological processes. Utilising distributed semantics is cost-effective due to pretrained language models’ availability. However, integrating perceptual data with semantic representations is crucial, as these representations are experience-based and may not fully capture complex sentences’ meaning. Future research can address questions like memorability using semantic representations and explore individual differences by training models on data from distinct sub-populations. High-dimensional representations from embedding models offer numerous opportunities to study human behaviour on a larger scale than previously possible.

Pro-social nudging has become a prominent strategy in behavioural public policy, aiming to encourage cooperative, altruistic or community-enhancing behaviours without coercion or significant economic incentives. By subtly altering the choice architecture or informational framing of decisions, pro-social nudges seek to elicit actions that benefit others, such as donating to charity, conserving energy, recycling, volunteering or adhering to public health measures. This chapter offers a critical, data-driven examination of pro-social nudging as a methodological and theoretical construct within behavioural data science. It traces the evolution of the concept from early experimental interventions to digitally enabled nudging in algorithmically mediated environments. The chapter investigates how pro-social nudges function across different domains and populations, evaluates the psychological mechanisms and empirical evidence behind their efficacy and considers the role of emerging technologies – such as AI, digital twins and real-time behavioural tracking – in designing, personalising and evaluating these interventions. Ethical concerns, including paternalism, manipulation and differential impacts across social groups, are addressed in depth. By integrating theoretical reflection with practical applications, this chapter highlights the importance of context-sensitive, transparent and equitable designs in pro-social nudging strategies. It concludes with a call for participatory co-design, longitudinal validation and interdisciplinary collaboration to ensure that pro-social nudges serve the public good without compromising autonomy or equity.

Human–machine teaming (HMT) represents a critical frontier in Behavioural Data Science, where cognitive, social, cultural and algorithmic factors converge within complex systems. While traditional human–computer interaction (HCI) research has explored usability and task efficiency, human–machine teaming introduces new imperatives: mutual predictability, adaptive trust calibration, shared mental models and contextually sensitive collaboration. These imperatives are increasingly important in sectors such as defence, healthcare, manufacturing and disaster response, where human and machine agents co-perform roles that require high-stakes coordination. This chapter integrates systems thinking and cross-cultural theory to provide a framework for understanding HMT through the lens of Behavioural Data Science. It examines how systemic factors – ranging from team topology to environmental volatility – influence teaming outcomes, and how cultural variation impacts expectations, acceptance and performance of AI teammates. Drawing on empirical case studies and simulation-based experiments, we identify design principles for effective teaming and highlight methodological challenges in measuring team efficacy and behavioural alignment. We also interrogate ethical and philosophical issues in the automation of team roles and decision-making authority. Ultimately, we argue that human–machine teaming is not merely a technological phenomenon, but a socio-technical system embedded within organisational, institutional and cultural structures. Behavioural Data Science is uniquely positioned to illuminate these interdependencies and guide the development of trustworthy, transparent and inclusive teaming frameworks.

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.

Walk into most large organisations and you’ll notice two distinct knowledge cultures – one fluent in human insight, the other fluent in data. This is a persistent divide – sometimes historical, sometimes epistemological – between two influential groups: behavioural scientists and data scientists. In the past, this divide was more visible, even physical. During the early data analytics era of the 1990s and early 2000s, data scientists were often ‘tucked away’ in back offices or lower floors – an arrangement at one point satirised by the British comedy The IT Crowd, where technical experts were literally hidden in the basement. Meanwhile, behavioural scientists – those working on organisational culture, consumer insights and human-centred design – tended to sit closer to the executive suite, advising leadership on strategy and the ‘why’ behind behaviour.