Brooke Leave Home is a personalized film designed to engage a non-expert audience with open data about the support young adults receive when leaving the care system in England. The film draws upon a range of video-based data storytelling techniques to present each viewer with a personalized perspective on the topic based on data from their own local area. We present the film's design and describe how its storytelling techniques were developed to support viewers in understanding, and fostering empathic connections with, the data sources featured and the implications they have for care leavers. We also present a study with 47 viewers, which explores how these techniques were experienced and how effective they were in aiding engagement with the data included and its meaning.

With technologies that afford much larger-scale data collection than previously imagined, new ways of processing and interpreting qualitative textual data are required. HCI researchers use a range of methods for interpreting the 'full range of human experience' from qualitative data, however, such approaches are not always scalable. Feminist geography seeks to explore how diverse and varied accounts of place can be understood and represented, whilst avoiding reductive classification systems. In this paper, we assess the extent to which unsupervised topic models can support such a research agenda. Drawing on literature from Feminist and Critical GIS, we present a case study analysis of a Volunteered Geographic Information dataset of reviews about breastfeeding in public spaces. We demonstrate that topic modelling can offer novel insights and nuanced interpretations of complex concepts such as privacy and be integrated into a critically reflexive feminist data analysis approach that captures and represents diverse experiences of place.

This article probes the practical ethical implications of AI system design by reconsidering the important topic of bias in the datasets used to train autonomous intelligent systems. The discussion draws on recent work concerning behaviour-guiding technologies, and it adopts a cautious form of technological utopianism by assuming it is potentially beneficial for society at large if AI systems are designed to be comparatively free from the biases that characterise human behaviour. However, the argument presented here critiques the common well-intentioned requirement that, in order to achieve this, all such datasets must be debiased prior to training. By focusing specifically on gender-bias in Neural Machine Translation (NMT) systems, three automated strategies for the removal of bias are considered – downsampling, upsampling, and counterfactual augmentation – and it is shown that systems trained on datasets debiased using these approaches all achieve general translation performance that is much worse than a baseline system. In addition, most of them also achieve worse performance in relation to metrics that quantify the degree of gender bias in the system outputs. By contrast, it is shown that the technique of domain adaptation can be effectively deployed to debias existing NMT systems after they have been fully trained. This enables them to produce translations that are quantitatively far less biased when analysed using gender-based metrics, but which also achieve state-of-the-art general performance. It is hoped that the discussion presented here will reinvigorate ongoing debates about how and why bias can be most effectively reduced in state-of-the-art AI systems.

This paper introduces a generic (i.e. production-independent) framework for OBM storytelling. Aiming to function as a complete end-to-end (from conception to realisation) reference for authoring OBM narrative content, it proposes an integrated model that includes the three essential levels: conceptual, technological and aesthetic. At the conceptual level, we introduce a set of abstractions which provide a unified reference for thinking, describing and analysing interactive narrative structures of OBM content. Their recursive nature make our model stand out in terms of its power of expression. These abstractions have direct one-to-one operational counterparts implemented in our productionindependent authoring toolkit Ð Cutting Room. This ensures that any specific story design within the proposed conceptual model is directly realisable as an OBM production. This isomorphic relationship between the abstract concepts and their operationalisation is another distinguishing aspect of our overall proposition. We have validated the model at the aesthetic level through the production of the interactive film What is Love?, experienced by over 900 people at the media art festival Mediale 2018 in York, UK, and evaluated through a dedicated questionnaire by 94 of them. As the foundations of OBM storytelling have not yet been established, we trust this paper constitutes a significant milestone in its development.

Clinical incident reporting provides opportunities for organisational learning, ideally leading to improved patient safety. However, this process requires healthcare professionals to record experiences where patients were harmed, or had the potential to be harmed. It also requires others to interpret the language used in order to make recommendations. We investigate the use of epistemic and evidential markers in incidents labelled as ‘user error’, in which a responsible individual is categorically implied, as opposed to other types of incidents where responsible individuals may not be tacitly assumed, such as ‘failure of sterilisation or contamination of equipment’ and ‘lack of suitably trained staff’. By analysing the frequency of various linguistic features related to authority and accountability, we provide insights into the pragmatics of clinical incident reporting. We find that user error reports differ from other categories of reports in that the identity of the narrator is obscured and the locus of agency is removed, and that this difference is irrespective to levels of patient harm. User error reports differ from other incident reports in the following statistically significant ways: they are more likely to be written using impersonal absent narration and feature significantly higher frequencies of epistemic markers of uncertainty and evidentiality