It is well known that utterances convey a great deal of information about the speaker in addition to their semantic content. One such type of information consists of cues to the speaker's personality traits, the most fundamental dimension of variation between humans. Recent work explores the automatic detection of other types of pragmatic variation in text and conversation, such as emotion, deception, speaker charisma, dominance, point of view, subjectivity, opinion and sentiment. Personality affects these other aspects of linguistic production, and thus personality recognition may be useful for these tasks, in addition to many other potential applications. However, to date, there is little work on the automatic recognition of personality traits. This article reports experimental results for recognition of all Big Five personality traits, in both conversation and text, utilising both self and observer ratings of personality. While other work reports classification results, we experiment with classification, regression and ranking models. For each model, we analyse the effect of different feature sets on accuracy. Results show that for some traits, any type of statistical model performs significantly better than the baseline, but ranking models perform best overall. We also present an experiment suggesting that ranking models are more accurate than multi-class classifiers for modelling personality. In addition, recognition models trained on observed personality perform better than models trained using selfreports, and the optimal feature set depends on the personality trait. A qualitative analysis of the learned models confirms previous findings linking language and personality, while revealing many new linguistic markers.

SummaryBackgroundRemote ischaemic conditioning with transient ischaemia and reperfusion applied to the arm has been shown to reduce myocardial infarct size in patients with ST-elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (PPCI). We investigated whether remote ischaemic conditioning could reduce the incidence of cardiac death and hospitalisation for heart failure at 12 months.MethodsWe did an international investigator-initiated, prospective, single-blind, randomised controlled trial (CONDI-2/ERIC-PPCI) at 33 centres across the UK, Denmark, Spain, and Serbia. Patients (age >18 years) with suspected STEMI and who were eligible for PPCI were randomly allocated (1:1, stratified by centre with a permuted block method) to receive standard treatment (including a sham simulated remote ischaemic conditioning intervention at UK sites only) or remote ischaemic conditioning treatment (intermittent ischaemia and reperfusion applied to the arm through four cycles of 5-min inflation and 5-min deflation of an automated cuff device) before PPCI. Investigators responsible for data collection and outcome assessment were masked to treatment allocation. The primary combined endpoint was cardiac death or hospitalisation for heart failure at 12 months in the intention-to-treat population. This trial is registered with ClinicalTrials.gov (NCT02342522) and is completed.FindingsBetween Nov 6, 2013, and March 31, 2018, 5401 patients were randomly allocated to either the control group (n=2701) or the remote ischaemic conditioning group (n=2700). After exclusion of patients upon hospital arrival or loss to follow-up, 2569 patients in the control group and 2546 in the intervention group were included in the intention-to-treat analysis. At 12 months post-PPCI, the Kaplan-Meier-estimated frequencies of cardiac death or hospitalisation for heart failure (the primary endpoint) were 220 (8·6%) patients in the control group and 239 (9·4%) in the remote ischaemic conditioning group (hazard ratio 1·10 [95% CI 0·91–1·32], p=0·32 for intervention versus control). No important unexpected adverse events or side effects of remote ischaemic conditioning were observed.InterpretationRemote ischaemic conditioning does not improve clinical outcomes (cardiac death or hospitalisation for heart failure) at 12 months in patients with STEMI undergoing PPCI.FundingBritish Heart Foundation, University College London Hospitals/University College London Biomedical Research Centre, Danish Innovation Foundation, Novo Nordisk Foundation, TrygFonden.

This paper addresses the problem of automatic speech recognition in the presence of interfering signals and noise with statistical characteristics ranging from stationary to fast changing and impulsive.A technique of signal decomposition using hidden Markov models, 111, is described. This is a generalisation of conventional hidden Markov modelling that provides an optimal method of decomposing simultaneous processes. The technique exploits the ability of hidden Markov models to model dynamically varying signals in order to accomodate concurrent processes, including interfering signals as complex as speech.This form of signal decomposition has wide implications for signal separation in general and improved speech modelling in particular. However, this paper concentrates on the application of decomposition to the problem of recognition of speech contaminated with noise.

There are a number of psychological phenomena in which dramatic emotional responses are evoked by seemingly innocuous perceptual stimuli. A well known example is the ‘uncanny valley’ effect whereby a near human-looking artifact can trigger feelings of eeriness and repulsion. Although such phenomena are reasonably well documented, there is no quantitative explanation for the findings and no mathematical model that is capable of predicting such behavior. Here I show (using a Bayesian model of categorical perception) that differential perceptual distortion arising from stimuli containing conflicting cues can give rise to a perceptual tension at category boundaries that could account for these phenomena. The model is not only the first quantitative explanation of the uncanny valley effect, but it may also provide a mathematical explanation for a range of social situations in which conflicting cues give rise to negative, fearful or even violent reactions.

No abstract