Prior Expectations Research Articles

Communication in healthcare: experience of students and professionals from teaching- learning to practice in health.

This study aimed to understand the teaching-learning experience in the Communication in Healthcare class among students, teaching assistants, and health professionals, as well as its applications to professional practice. This is a qualitative study with a theoretical approach based on Gadamer's Philosophical Hermeneutics and a methodological framework based on Minayo and Bardin's thematic content analysis. Communication in Healthcare is an elective multiprofessional class, which lasts one semester and is offered regularly. All former students (n = 368) were invited to participate by email, and 30 participated in these focus groups (13 students, 8 teaching assistants, and 9 health professionals). The online focus groups took place on an online platform, and they were video-recorded and subsequently transcribed. Through cross-sectional and vertical analysis, the main themes were identified. The Communication in Healthcare class was an important step for personal, professional, and interprofessional formation and development of communication competence. The following dominant themes were identified: 1) motivation for signing up, 2) prior expectations, 3) meaning of the experience and shaping moments, 4) how the teaching-learning experience was retained and what was retained, 5) repercussions in relation to self, others, and professional life, and 6) reflections about the curriculum, interprofessional dialogue, and formation. The teaching-learning experience was important for the formation of communicational competence. This research contributes to medical education and opens teaching-learning paths for communication skills, empathy, dialogue, and interprofessionalism. Future studies with a philosophical hermeneutic framework and online focus groups are indicated for the comprehension of educational interventions in health.

The Human Centromedial Amygdala Contributes to Negative Prediction Error Signaling during Appetitive and Aversive Pavlovian Gustatory Learning.

Prediction error (PE) is the mismatch between a prior expectation and reality, and it lies at the core of associative learning about aversive and appetitive stimuli. Human studies on fear learning have linked the amygdala to aversive PEs. In contrast, the relationship between the amygdala and PE in appetitive settings and stimuli, unlike those that induce fear, has received less research attention. Animal studies show that the amygdala is a functionally heterogeneous structure. Nevertheless, the role of the amygdala nuclei in PE signaling remains unknown in humans. To clarify the role of two subdivisions of the human amygdala, the centromedial amygdala (CMA) and basolateral amygdala (BLA), in appetitive and aversive PE signaling, we used gustatory pavlovian learning involving eating-related naturalistic outcomes. Thirty-eight right-handed individuals (19 females) participated in the study. We found that surprise with neutral feedback when a reward is expected triggers activity within the left and right CMA. When an aversive outcome is expected, surprise with neutral feedback triggers activity only within the left CMA. Notably, the BLA was not activated by those conditions. Thus, the CMA engages in negative PE signaling during appetitive and aversive gustatory pavlovian learning, whereas the BLA is not critical for this process. In addition, PE-related activity within the left CMA during aversive learning is negatively correlated with neuroticism and positively correlated with extraversion. The findings indicate the importance of the CMA in gustatory learning when the value of outcomes changes and have implications for understanding psychological conditions that manifest perturbed processing of negative PEs.SIGNIFICANCE STATEMENT A discrepancy between a prediction and an actual outcome (PE) plays a crucial role in learning. Learning improves when an outcome is more significant than expected (positive PE) and worsens when it is smaller than expected (negative PE). We found that the negative PE during appetitive and aversive taste learning is associated with increased activity of the CMA, which suggests that the CMA controls taste learning. Our findings may have implications for understanding psychological states associated with deficient learning from negative PEs, such as obesity and addictive behaviors.

Virtual Reflection Group Meetings as a Structured Active Learning Method to Enhance Perceived Competence in Critical Care: Focus Group Interviews With Advanced Practice Nursing Students

Advanced practice nurses (APNs) are in high demand in critical care units. In Norway, APNs are educated at the master's degree level and acquire the competence to ensure the independent, safe, and effective treatment of patients in constantly and rapidly changing health situations. APNs' competence embraces expert knowledge and skills to perform complex decision-making in the clinical context; therefore, it is essential that educational institutions in nursing facilitate learning activities that ensure and improve students' achievement of the required competence. In clinical practice studies of APN education, face-to-face reflection group (FFRG) meetings, held on campus with the participation of a nurse educator and advanced practice nursing students (APNSs), are a common learning activity to improve the competence of APNSs. Although FFRG meetings stimulate APNSs' development of required competencies, they may also result in unproductive academic discussions, reduce the time that APNSs spend in clinical practice, and make it impossible for nurse preceptors (NPs) to attend the meetings, which are all challenges that need to be addressed. This study aimed to address the challenges experienced in FFRG meetings by implementing virtual reflection group (VRG) meetings and to explore the experiences of APNSs, NPs, and nurse educators in VRG meetings as an active learning method supported by technology to stimulate students' development of the required competence to become APNs in critical care. This study adopted a qualitative explorative design with 2 focus group interviews and used inductive content analysis to explore the collected data. The main finding is that reflection group meetings supported by technology resulted in a better-structured active learning method. The VRG meeting design allowed APNSs to spend more time in clinical practice placements. The APNSs and NPs experienced that they participated actively and effectively in the meetings, which led to a perceived increase in competence. The APNSs also perceived an improved learning experience compared with their prior expectations. Users perceived that the implemented novel teaching design supported by technology, the VRG meeting, was a more effective method than FFRG meetings on campus to develop APNSs' required competence in critical care. The VRG was also perceived as an improved method to solve the challenges encountered in FFRG meetings. Specifically, the APNSs felt that they were prepared to undertake complex decision-making with a higher level of analytic cognition in a clinical context and to lead professional discussions in the ward. This developed teaching design can easily be adapted to diverse educational programs at various levels of professional education.

Natural conversations with a virtual being: How user experience with a current conversational AI model compares to expectations

AbstractThe present work investigates the effect of natural conversations with virtual beings on user perceptions with a current conversational AI model (Meta's BlenderBot). To this aim, we designed a virtual being from a deep learning‐generated face and a conversational AI model acting as a virtual conversation partner in an online conferencing software and evaluated it in 11 perceptions of social attributes. Compared to prior expectations, participants perceived the virtual being as distinctly higher in warmth (engaging, empathic, and approachable) but lower in realism and credibility after 5 days of 10 min daily conversations (Study 1). Further, we explored the idea of simplifying the technical setup to reduce the technical entry barrier for such AI applications (Study 2). To this aim, we conducted several trials of fine‐tuning a small conversational model of 90 million parameters until its performance metrics improved. Testing this fine‐tuned model with users revealed that this model was not perceived differently from a large conversational model (1.4 billion parameters). In summary, our findings show that recent progress in conversational AI has added warmth‐related aspects to the user experience with virtual beings, and that fine‐tuning a conversational AI model can be effective to reduce technical complexity.

Evidence of environmental urban design parameters that increase and reduce sense of place in Barcelona (Spain)

Urban planning design considers sense of place attributed to the environment because it is important to quality of life and influences citizen support for planning proposals. In this paper, the physical and geographic characteristics that increase and decrease levels of sense of place were analyzed. Mediation effects of prior expectations and belief in urban legends attributed to specific environments were controlled for. A total of 1727 residents from 10 different districts of the city of Barcelona participated. Empirical urban parameters were measured for each district (e.g., hectares of parks and rate of streets with noise above 60 dB) and the weight with which they predicted levels of sense of place was objectively quantified. Perceived quality of life and residents' positive expectations of green spaces were measured also. Structural equation modeling (SEM) assessed theory relating green environments to sense of place and tested which urban elements had a detrimental effect. When including the mediating effects of prior expectations and perceived quality of life, urban parameters related to green spaces predicted increases in sense of place between 11% and 40%. Decibels, pedestrian streets, and the number of police arrests predicted systematic reductions in sense of place between 18% and 20%. Accordingly, the authors proposed two urban models of positive and negative feedback on sense of place. Application of these will improve urban planning by enhancing decision making efficacy.

Mental health meets computational neuroscience: A predictive Bayesian account of the relationship between interoception and multisensory bodily illusions in anorexia nervosa

Mental health disorders pose a significant challenge to society. The Bayesian perspective on the mind offers unique insights and tools that may help address a variety of mental health conditions. Psychopathological dysfunctions are often connected to altered predictive and active inference processes, in which cognitive and physiological pathogenic beliefs shape the clinical condition and its symptoms. However, there is a lack of general empirical models that integrate cognitive beliefs, physiological experience, and symptoms in healthy and clinical populations. In this study, we examined the relationship between altered predictive mechanisms, interoception, and pathological bodily distortions in healty individuals and in individuals suffering from anorexia nervosa (AN). AN patients (N=15) completed a Virtual Reality Full-Body Illusion along with interoceptive tasks twice: at hospital admission during an acute symptomatological phase (Time 1) and after a 12-week outpatient clinical weight-restoring rehabilitative program (Time 2). Results were compared to a healthy control group. Our findings indicated that higher levels of interoceptive metacognitive awareness were associated with a greater embodiment. However, unlike in healthy participants, AN patients' interoceptive metacognition was linked to embodiment even in multisensory mismatching (asynchronous) conditions. In addition, unlike in healthy participants, higher interoceptive metacognition in AN patients was related to prior abnormal bodily distortions during the acute symptomatology phase. Prediction errors in bodily estimates predicted posterior bodily estimate distortions after the illusion, but while this relationship was only significant in the synchronous condition in healthy participants, there was no significant difference between synchronous and asynchronous conditions in AN patients. Despite the success of the rehabilitation program in restoring some dysfunctional patterns in the AN group, prediction errors and posterior estimate distortions were present at hospital discharge. Our findings suggest that individuals with AN prioritize interoceptive metacognitive processes (i.e., confidence in their own perceived sensations rather than their actual perceptions), disregarding bottom-up bodily inputs in favour of their prior altered top-down beliefs. Moreover, even if the rehabilitative program partially mitigated these alterations, the pathological condition impaired the patients' ability to coherently update their prior erroneous expectations with real-time multisensory bottom-up bodily information, possibly locking the patients in the experience of a distorted prior top-down belief. These results suggest new therapeutic perspectives and introduce the framework of regenerative virtual therapy (RVT), which aims at utilizing technology-based somatic modification techniques to restructure the maladaptive priors underlying a pathological condition.

Enhancing Bayesian Approaches in the Cognitive and Neural Sciences via Complex Dynamical Systems Theory

In the cognitive and neural sciences, Bayesianism refers to a collection of concepts and methods stemming from various implementations of Bayes’ theorem, which is a formal way to calculate the conditional probability of a hypothesis being true based on prior expectations and updating priors in the face of errors. Bayes’ theorem has been fruitfully applied to describe and explain a wide range of cognitive and neural phenomena (e.g., visual perception and neural population activity) and is at the core of various theories (e.g., predictive processing). Despite these successes, we claim that Bayesianism has two interrelated shortcomings: its calculations and models are predominantly linear and noise is assumed to be random and unstructured versus deterministic. We outline ways that Bayesianism can address those shortcomings: first, by making more central the nonlinearities characteristic of biological cognitive systems, and second, by treating noise not as random and unstructured dynamics, but as the kind of structured nonlinearities of complex dynamical systems (e.g., chaos and fractals). We provide bistable visual percepts as an example of a real-world phenomenon that demonstrates the fruitfulness of integrating complex dynamical systems theory in Bayesian treatments of perception. Doing so facilitates a Bayesianism that is more capable of explaining a number of currently out-of-reach natural phenomena on their own, biologically realistic terms.

β-Bursts over Frontal Cortex Track the Surprise of Unexpected Events in Auditory, Visual, and Tactile Modalities.

One of the fundamental ways in which the brain regulates and monitors behavior is by making predictions about the sensory environment and adjusting behavior when those expectations are violated. As such, surprise is one of the fundamental computations performed by the human brain. In recent years, it has been well established that one key aspect by which behavior is adjusted during surprise is inhibitory control of the motor system. Moreover, because surprise automatically triggers inhibitory control without much proactive influence, it can provide unique insights into largely reactive control processes. Recent years have seen tremendous interest in burst-like β frequency events in the human (and nonhuman) local field potential-especially over (p)FC-as a potential signature of inhibitory control. To date, β-bursts have only been studied in paradigms involving a substantial amount of proactive control (such as the stop-signal task). Here, we used two cross-modal oddball tasks to investigate whether surprise processing is accompanied by increases in scalp-recorded β-bursts. Indeed, we found that unexpected events in all tested sensory domains (haptic, auditory, visual) were followed by low-latency increases in β-bursting over frontal cortex. Across experiments, β-burst rates were positively correlated with estimates of surprise derived from Shannon's information theory, a type of surprise that represents the degree to which a given stimulus violates prior expectations. As such, the current work clearly implicates frontal β-bursts as a signature of surprise processing. We discuss these findings in the context of common frameworks of inhibitory and cognitive control after unexpected events.

Rising to the Occasion: The Importance of the Pandemic for Faculty Adoption Patterns

Technology adoption patterns, in general, have been shown to have a common set of predictive factors such as performance expectancy, social influence, voluntariness, effort expectancy, and facilitating conditions. However, the significance of such factors varies dramatically by situation and conditions. In the faculty adoption of online teaching modalities, three conditions were investigated in a university case study with 180 faculty respondents. Using the unified theory of acceptance and use of technology model, participants were asked to respond to questions about these factors prior to the pandemic, their perceptions about continuing pre-pandemic use in the future, and their perceptions about increasing pre-pandemic adoption of online teaching in the future. Critical to prior expectations were performance expectancy and level of effort. Continued use relied on all five factors, but only the negative aspects of social influence were significant. Factors affecting increased adoption (assuming voluntariness) were performance expectancy and facilitating conditions. Findings suggest that increased exposure to online teaching may not be as crucial as the quality of faculty experiences during the pandemic. The rationale for these factor shifts is provided, the effects of institutional support are discussed, the threats and limitations to generalizability are reviewed, and the ramifications for institutions trying to enhance faculty adoption are summarized.

Abstract P500: Age-Specific Population Attributable Fractions for the Impact of Hypertension on Dementia Risk

Introduction: Hypertension in midlife, but not late life, is a robust predictor of subsequent dementia. However, the fraction of dementia attributable to hypertension might vary depending on the age of the population considered, and the age through which dementia onset occurs. Here, we investigated associations of hypertension assessed at various ages with incident dementia by age 80 or 90, then estimated population attributable fractions (PAF) for dementia from hypertension categories at each of these age groups. Hypothesis: Given hypertension prevalence increases with age but its relative risk for dementia tends to decrease, we had no prior expectation of the age at which the PAF’s would be highest. We hypothesized, however, that PAFs for incident dementia would be higher when hypertension is measured in midlife age groups versus late-life age groups. Methods: We leveraged 32 years of follow-up data from the Atherosclerosis Risk in Communities study (ARIC), a prospective, community-based cohort that enrolled participants aged 45-64 years from four US communities (Washington County, MD; Forsyth County, NC; Jackson, MS; and selected suburbs of Minneapolis, MI) at ARIC visit 1 (1987-1989). Participants were followed through 2018-2019. We used Cox proportional hazards models to estimate hazard ratios, then quantified PAFs, of dementia by age 80 and 90 from hypertension assessed at ages of 45-54 (ARIC visit 1), 55-64 (ARIC visits 1 and 4), 65-74 (ARIC visits 4 and 5), and 75-84 (ARIC visit 5). Results: Hypertension was assessed among 7,572 participants aged 45-54; 12,033 aged 55-64; and 6,561 aged 65-74. By age 80 the number identified as having incident dementia was 711, 910, and 372, respectively. Relative to normotension, hypertension in each age category was associated with hazard ratios (HRs) greater than 1.0 for dementia from hypertension by age 80. The PAF for dementia by age 80 from hypertension measured at age 45-54 was 15.3% (95% CI = 6.9, 22.3%), 19.1% (95% CI = 9.9, 26.9%) at ages 55-64, and 19.9% (95% CI = -4.4, 38.5%) at ages 65-74. By age 90, the number of incident dementia cases were 958; 2,302; and 1,327, respectively; and, among the 2,086 participants aged 75-84, 400 incident dementia cases. HRs were slightly smaller than those by age 80, while hypertension assessed in the 75-84 age group was not significant. The PAFs for dementia by age 90 from hypertension at age 45-54 was 13.8% (95% CI = 6.6, 20.0%), 12.9% (95% CI = 7.0, 18.2%) at ages 55-64, 10.9% (95% CI = 0.02, 21.0%) at ages 65-74, and non-significant at ages 75-84. Conclusions: Public health interventions targeting hypertension in midlife through early late-life might reduce a sizeable proportion of dementia cases.

Variation in leisure sport conflicts and coping strategies depending on participation type and proximity during the COVID-19 pandemic.

New conflict types have arisen in leisure sports activities due to social regulations designed to address COVID-19. We analyze the differences in conflict-inducing factors and coping strategies across various types of leisure sports and levels of spatial proximity. Korean adults aged between 20 and 60 years, who had participated in leisure sports activities since the COVID-19 outbreak in January 2020, were surveyed, and 508 responses were collected for analysis. The differences in leisure sports conflicts and coping strategies across the types of leisure sports participation and spatial proximity were tested. The results show that conflict due to prejudice was higher in typical indoor sports activities, such as Pilates, yoga, and gym workouts, whereas conflict due to competition or not observing etiquette was higher in indoor golf. Second, conflict due to prior expectations and prejudice was high in outdoor sports activities, such as jogging and hiking. Finally, all participants showed avoidance behavior, but it was observed more frequently in outdoor sports than indoor sports. The study reveals how much leisure conflict is induced by various types of leisure sports participation, particularly during outdoor activities, which usually feature a relatively low density of participants. It underscores the necessity of developing structural approaches to resolving leisure conflicts in dangerous spaces or requiring intensive management and creating new leisure sports activities.

A novel computational approach to pain perception modelling within a Bayesian framework using quantitative sensory testing

Pain perception can be studied as an inferential process in which prior information influences the perception of nociceptive input. To date, there are no suitable psychophysical paradigms to measure this at an individual level. We developed a quantitative sensory testing paradigm allowing for quantification of the influence of prior expectations versus current nociceptive input during perception. Using a Pavlovian-learning task, we investigated the influence of prior expectations on the belief about the varying strength of association between a painful electrical cutaneous stimulus and a visual cue in healthy subjects (N = 70). The belief in cue-pain associations was examined with computational modelling using a Hierarchical Gaussian Filter (HGF). Prior weighting estimates in the HGF model were compared with the established measures of conditioned pain modulation (CPM) and temporal summation of pain (TSP) assessed by cuff algometry. Subsequent HGF-modelling and estimation of the influence of prior beliefs on perception showed that 70% of subjects had a higher reliance on nociceptive input during perception of acute pain stimuli, whereas 30% showed a stronger weighting of prior expectations over sensory evidence. There was no association between prior weighting estimates and CPM or TSP. The data demonstrates relevant individual differences in prior weighting and suggests an importance of top-down cognitive processes on pain perception. Our new psychophysical testing paradigm provides a method to identify individuals with traits suggesting greater reliance on prior expectations in pain perception, which may be a risk factor for developing chronic pain and may be differentially responsive to learning-based interventions.

On the functional form of the radial acceleration relation

ABSTRACTWe apply a new method for learning equations from data – Exhaustive Symbolic Regression (ESR) – to late-type galaxy dynamics as encapsulated in the radial acceleration relation (RAR). Relating the centripetal acceleration due to baryons, gbar, to the total dynamical acceleration, gobs, the RAR has been claimed to manifest a new law of nature due to its regularity and tightness in agreement with Modified Newtonian Dynamics (MOND). Fits to this relation have been restricted by prior expectations to particular functional forms, while ESR affords an exhaustive and nearly prior-free search through functional parameter space to identify the equations optimally trading accuracy with simplicity. Working with the SPARC data, we find the best functions typically satisfy gobs ∝ gbar at high gbar, although the coefficient of proportionality is not clearly unity and the deep-MOND limit $g_\text{obs}\propto \sqrt{g_\text{bar}}$ as gbar → 0 is little evident at all. By generating mock data according to MOND with or without the external field effect, we find that symbolic regression would not be expected to identify the generating function or reconstruct successfully the asymptotic slopes. We conclude that the limited dynamical range and significant uncertainties of the SPARC RAR preclude a definitive statement of its functional form, and hence that this data alone can neither demonstrate nor rule out law-like gravitational behaviour.

The Impact of Altimetry Corrections of Sentinel-3A Sea Surface Height in the Coastal Zone of the Northwest Atlantic

Corrections to altimeter-measured sea surface height anomalies (SSHA) have a larger proportional effect for synthetic aperture radar (SAR) altimetry than conventional, pulse-limited altimetry because of lower range noise. Here, we quantified the impact of the current generation of altimeter corrections in the coastal zone of the Northwest Atlantic, a region with significant dynamic activity. In this study, we used the sea level variance analysis to determine the change in variance for the altimeter corrections—range, geophysical, and mean surface—compared to the baseline. We also evaluated the performance of two coastal retrackers, ALES (empirical) and SAMOSA++ (fully analytical), against the SSHA from the Radar Altimeter Database System (RADS), which uses the standard SAR retracker. Tide corrections caused the largest change in sea level variance, followed by wet tropospheric corrections and sea state bias. Most non-standard altimeter corrections failed to reduce the sea level variance and performed markedly worse closer to the coast. Coastal retrackers showed a higher deviation from the standard SSHA closer to the coast, especially when the backscatter coefficient was high and the significant wave height was low. We conclude that further development of coastal corrections is needed. Contrary to our prior expectation, we found that standard altimetry corrections appear to perform as well as alternative more advanced/tailored corrections.

Visual illusions in young people reporting psychotic-like experiences

Background and objectivesA disruption in the co-ordination of bottom-up and top-down processing is thought to underlie anomalous perceptual experiences in psychosis. Visual illusions represent a valuable methodology in exploring this disruption. Here, we examined visual illusions in a group of young people having psychotic-like experiences. We also examined the relationship between illusion susceptibility and appraisal of psychotic-like experiences as well as depression, anxiety and stress levels. Method25 young people reporting psychotic-like experiences and 53 healthy participants performed an adjustment task that measured susceptibility to a battery of 13 visual illusions. Levels of depression, anxiety and stress were quantified in both groups. The clinical group also completed measures examining frequency, appraisals and emotional responses to psychotic-like experiences. ResultsA general increase of illusion susceptibility was found in the clinical group compared to the control group. However, when depression, anxiety and stress levels were controlled for, this difference disappeared. Stress turned out to be the best predictor of illusion susceptibility in the clinical group, whereas anomalous experiences, depression and anxiety were unrelated to overall illusion strength. LimitationsThis study is limited to young participants reporting significant mental health difficulties and psychotic-like experiences. Findings should be replicated in an Ultra High Risk (prodromal) group. ConclusionsIncreased levels of stress explained the enhanced vulnerability to illusions in the clinical group. This increased susceptibility suggests a perceptual style that relies too heavily on prior expectations at the expense of the true sensory evidence, potentially leading to an altered perceptual experience of the world.

Multivariate functional neuroimaging analyses reveal that strength-dependent face expectations are represented in higher-level face-identity areas

Perception is an active inference in which prior expectations are combined with sensory input. It is still unclear how the strength of prior expectations is represented in the human brain. The strength, or precision, of a prior could be represented with its content, potentially in higher-level sensory areas. We used multivariate analyses of functional resonance imaging data to test whether expectation strength is represented together with the expected face in high-level face-sensitive regions. Participants were trained to associate images of scenes with subsequently presented images of different faces. Each scene predicted three faces, each with either low, intermediate, or high probability. We found that anticipation enhances the similarity of response patterns in the face-sensitive anterior temporal lobe to response patterns specifically associated with the image of the expected face. In contrast, during face presentation, activity increased for unexpected faces in a typical prediction error network, containing areas such as the caudate and the insula. Our findings show that strength-dependent face expectations are represented in higher-level face-identity areas, supporting hierarchical theories of predictive processing according to which higher-level sensory regions represent weighted priors.

The Quixotic Quest for Objectivity in Observation

The Quixotic Quest for Objectivity in Observation

What came before: Assimilation effects in the categorization of time intervals

Assimilation is the process by which one judgment tends to approach some aspect of another stimulus or judgment. This effect has been known for over half a century in various domains such as the judgment of weight or sound intensity. However, the assimilation of judgments of durations have been relatively unexplored. In the current article, we present the results of five experiments in which participant s were required to judge the duration of a visual stimulus on each trial. In each experiment, we manipulated the pattern of durations they experienced in order to systematically separate the effects of the objective and subjective duration of stimuli on subsequent judgments. We found that duration judgments were primarily driven by prior judgments, with little, if any, effect of the prior objective stimulus duration. This is in contrast to the findings previously reported in regards to non-temporal judgments. We propose two mechanist explanations of this effect; a representational account in which judgments represent the speed of an underlying pacemaker, and an assimilation account in which judgment is based in prior experience. We further discuss results in terms of predictive coding, in which the previous rating is representative of a prior expectation, which is modified by current experience.

A Theory-Driven Deep Learning Method for Voice Chat–Based Customer Response Prediction

A Theory-Driven Deep Learning Method for Voice Chat–Based Customer Response Prediction In this study, we target the task of voice chat–based customer response prediction in an emerging online interaction–based commercial mode, the invite-online-and-experience-in-store mode. Prior research shows that satisfaction, which can be revealed by the discrepancy between prior expectation and actual experience, is a key factor to disentangle customers’ purchase intention, whereas black box deep learning methods empirically promise us with advantageous capabilities in dealing with complex voice data, for example, text and audio information incorporated in voice chat. To this end, we propose a theory-driven deep learning method that enables us to (1) learn customers’ personalized product preferences and dynamic satisfaction in the absence of their profile information, (2) model customers’ actual experiences based on multiview voice chat information in an interlaced way, and (3) enhance the customer response prediction performance of a black box deep learning model with theory-driven dynamic satisfaction. Empirical evaluation results demonstrate the advantageous prediction performance of our proposed method over state-of-the-art deep learning alternatives. Investigation of cumulative satisfaction reveals the collaborative predictive roles of theory-driven dynamic satisfaction and deep representation features for customer response prediction. Explanatory analysis further renders insights into customers’ personalized preferences and dynamic satisfaction for key product attributes.

Long COVID as a Functional Somatic Symptom Disorder Caused by Abnormally Precise Prior Expectations During Bayesian Perceptual Processing: A New Hypothesis and Implications for Pandemic Response

Long COVID as a Functional Somatic Symptom Disorder Caused by Abnormally Precise Prior Expectations During Bayesian Perceptual Processing: A New Hypothesis and Implications for Pandemic Response