Social Behavioral Data Research Articles

Evaluating the Effectiveness of Social Recommender Systems on Consumer Satisfaction and Purchase Intentions

With the widespread adoption of social media platforms, consumers increasingly rely on recommendations from social networks. Simultaneously, mutual recommendations among family and friends also play a significant role in purchase decisions. Social recommendation systems analyze users' social networks, behavioral data, and interest preferences to recommend personalized products or services. This method enhances the accuracy and relevance of recommendations, increases users' trust and satisfaction, and boosts merchants' revenues. This study aims to investigate the impact of social recommendation systems (such as friend recommendations and social media recommendations) on consumer purchase decisions. The primary objectives of this research include: Firstly, examining the role of friend recommendations in the consumer decision-making process and exploring their impact on enhancing consumers' trust and purchase intentions. Secondly, studying the accuracy of recommendation algorithms to understand their effect on meeting consumer needs and influencing purchase intentions. Thirdly Based on the research findings, providing reference suggestions for optimizing recommendation systems to e-commerce platforms, brick-and-mortar retailers, and merchants, assisting them in formulating precise marketing strategies. Through this study, we hope to offer new insights to both academia and industry, promoting the further development and application of social recommendation systems. Additionally, we aim to provide valuable theoretical support and practical guidance for optimizing recommendation systems on e-commerce platforms, for brick-and-mortar retailers, and for merchants.

Problems of determining the borrower's creditworthiness

This article addresses the challenges associated with determining the borrower's creditworthiness. The authors define the borrower's creditworthiness as the ability to timely and fully meet debt obligations to the lender. This determination is based on an evaluation of the borrower's financial condition, forecast of business development, and other factors influencing the ability to repay the loan.
 The authors identify internal and external factors affecting the creditworthiness of borrowers in Ukraine. Internal factors include the economic situation, regulatory policies, credit history, credit rating, and a lack of financial literacy. External factors encompass the global economic situation and the political climate.
 The article also discusses challenges in determining the borrower's creditworthiness during times of war. The authors note that creditworthiness can sharply decrease during such periods due to factors such as reduced income, increased costs, decreased demand for goods and services, and an unstable economic situation.
 To address these challenges during wartime, the authors propose the following recommendations:
 
 Widespread use of artificial intelligence: AI enables the consideration of more factors affecting the borrower's creditworthiness and the adaptation of credit scoring models to changes in the economic situation.
 Expansion of data on the borrower's financial condition: Financial institutions should utilize more data sources, including unstructured data such as social media and behavioral data, to assess the borrower's financial condition.
 Development of new methods for assessing creditworthiness: Financial institutions should create new methods that account for the specific conditions of wartime.
 Establishment of cooperation between financial institutions and government agencies: This collaboration will provide additional data on the financial condition of borrowers, offering financial institutions a more comprehensive view.
 Promotion of financial literacy among the population: Improving financial literacy will empower borrowers to better understand their financial obligations and make more informed lending decisions.
 
 Implementing these recommendations will enable financial institutions to enhance the accuracy of creditworthiness assessments and, consequently, reduce credit risks during times of war.

Are we braver in cyberspace? Social media anonymity enhances moral courage

The literature has established accumulated evidence on the negative consequences of social media anonymity on behaviors online (e.g., cyber-aggression). Yet the potential benefits of social media anonymity have been largely overlooked, especially when it comes to prosociality. In four studies, we examined the facilitating effect of perceived social media anonymity on online moral courage. We first tested and confirmed the relation of perceived social media anonymity to online moral courage in a correlational study (Study 1) and an experimental study (Study 2). We then tested and revealed the mediating role of perceived risk and the moderating role of moral meaningfulness in the relation between perceived anonymity and moral courage (Study 3). We further used social media behavioral data to examine the association between social media anonymity and moral courage in an ecologically valid context (Study 4). Our findings enrich the research of moral psychology and social media studies by providing the first experimental evidence for the prosocial effect of social media anonymity. They further have important implications for website interface design, social activism, as well as intervention programs to promote constructive civil engagement online.

Identifying Chinese social media users' need for affect from their online behaviors.

The need for affect (NFA), which refers to the motivation to approach or avoid emotion-inducing situations, is a valuable indicator of mental health monitoring and intervention, as well as many other applications. Traditionally, NFA has been measured using self-reports, which is not applicable in today's online scenarios due to its shortcomings in fast, large-scale assessments. This study proposed an automatic and non-invasive method for recognizing NFA based on social media behavioral data. The NFA questionnaire scores of 934 participants and their social media data were acquired. Then we run machine learning algorithms to train predictive models, which can be used to automatically identify NFA degrees of online users. The results showed that Extreme Gradient Boosting (XGB) performed best among several algorithms. The Pearson correlation coefficients between predicted scores and NFA questionnaire scores achieved 0.25 (NFA avoidance), 0.31 (NFA approach) and 0.34 (NFA total), and the split-half reliabilities were 0.66-0.70. Our research demonstrated that adolescents' NFA can be identified based on their social media behaviors, and opened a novel way of non-intrusively perceiving users' NFA which can be used for mental health monitoring and other situations that require large-scale NFA measurements.

Nest-sharing behavior of captive Broad-snouted caimans (Caiman latirostris): cooperation or exploitation?

Abstract Communal egg-laying is not frequently observed in crocodilians that exhibit nest attendance. However, it has been reported for both wild and captive Caiman latirostris. To understand the proximate causes of communal nesting, we aim to describe the nesting behavior of caimans during communal egg-laying in a captive population. Video cameras were placed at nests and the behavior of females was monitored throughout three incubation periods. We documented and analyzed social behavioral data. Nest-sharing behavior consisted of several females congregating and performing nest construction, nest vigilance and nest maintenance. It was observed in all nests previous to egg-laying. After the first laying, one female prevented others from approaching. The second egg-laying female negatively affected the previous clutch. Working together at the same nest would appear to be an exploitative rather than a cooperative activity, and communal nesting could be a competitive interaction, due to limited suitable nesting sites or overcrowding due to captivity.

How Dissemination and Implementation Science Can Contribute to the Advancement of Learning Health Systems.

Many health systems are working to become learning health systems (LHSs), which aim to improve the value of health care by rapidly, continuously generating evidence to apply to practice. However, challenges remain to advance toward the aspirational goal of becoming a fully mature LHS. While some important challenges have been well described (i.e., building system-level supporting infrastructure and the accessibility of inclusive, integrated, and actionable data), other key challenges are underrecognized, including balancing evaluation rapidity with rigor, applying principles of health equity and classic ethics, focusing on external validity and reproducibility (generalizability), and designing for sustainability. Many LHSs focus on continuous learning cycles, but with limited consideration of issues related to the rapidity of these learning cycles, as well as the sustainability or generalizability of solutions. Some types of data have been consistently underrepresented, including patient-reported outcomes and preferences, social determinants, and behavioral and environmental data, the absence of which can exacerbate health disparities. A promising approach to addressing many challenges that LHSs face may be found in dissemination and implementation (D&I) science. With an emphasis on multilevel dynamic contextual factors, representation of implementation partner engagement, pragmatic research, sustainability, and generalizability, D&I science methods can assist in overcoming many of the challenges facing LHSs. In this article, the authors describe the current state of LHSs and challenges to becoming a mature LHS, propose solutions to current challenges, focusing on the contributions of D&I science with other methods, and propose key components and characteristics of a mature LHS model that others can use to plan and develop their LHSs.

Signaling Nothing: Motivating the Masses with Status Signals That Encourage Anti-Consumption

Anti-consumption is arguably the most impactful environmentally friendly behavior but can be very challenging for consumers and antithetical to marketing. However, it may be possible for brands to support consumers in difficult anti-consumption actions. This paper demonstrates that a conspicuous signal communicating environmental motives can encourage anti-consumption, particularly for consumers least likely to do so without it. Real social media behavioral data and two experiments show that willingness to engage in anti-consumption practices can be enhanced with use of conspicuous anti-consumption signals, specifically for consumers low-to-moderate on environmental concern and moderate-to-high on need for status, while increasing willingness-to-pay. This type of consumer is unlikely to be intrinsically motivated to reduce consumption and much more common than extremely green consumers, potentially resulting in very large positive impact. If more brands support reduced consumption, the dominant social paradigm around marketing and ever-increasing consumption could begin to shift for the good of the planet.

Iterative data-driven forecasting of the transmission and management of SARS-CoV-2/COVID-19 using social interventions at the county-level

The control of the initial outbreak and spread of SARS-CoV-2/COVID-19 via the application of population-wide non-pharmaceutical mitigation measures have led to remarkable successes in dampening the pandemic globally. However, with countries beginning to ease or lift these measures fully to restart activities, concern is growing regarding the impacts that such reopening of societies could have on the subsequent transmission of the virus. While mathematical models of COVID-19 transmission have played important roles in evaluating the impacts of these measures for curbing virus transmission, a key need is for models that are able to effectively capture the effects of the spatial and social heterogeneities that drive the epidemic dynamics observed at the local community level. Iterative forecasting that uses new incoming epidemiological and social behavioral data to sequentially update locally-applicable transmission models can overcome this gap, potentially resulting in better predictions and policy actions. Here, we present the development of one such data-driven iterative modelling tool based on publicly available data and an extended SEIR model for forecasting SARS-CoV-2 at the county level in the United States. Using data from the state of Florida, we demonstrate the utility of such a system for exploring the outcomes of the social measures proposed by policy makers for containing the course of the pandemic. We provide comprehensive results showing how the locally identified models could be employed for accessing the impacts and societal tradeoffs of using specific social protective strategies. We conclude that it could have been possible to lift the more disruptive social interventions related to movement restriction/social distancing measures earlier if these were accompanied by widespread testing and contact tracing. These intensified social interventions could have potentially also brought about the control of the epidemic in low- and some medium-incidence county settings first, supporting the development and deployment of a geographically-phased approach to reopening the economy of Florida. We have made our data-driven forecasting system publicly available for policymakers and health officials to use in their own locales, so that a more efficient coordinated strategy for controlling SARS-CoV-2 region-wide can be developed and successfully implemented.

Lifetime stability of social traits in bottlenose dolphins

Behavioral phenotypic traits or “animal personalities” drive critical evolutionary processes such as fitness, disease and information spread. Yet the stability of behavioral traits, essential by definition, has rarely been measured over developmentally significant periods of time, limiting our understanding of how behavioral stability interacts with ontogeny. Based on 32 years of social behavioral data for 179 wild bottlenose dolphins, we show that social traits (associate number, time alone and in large groups) are stable from infancy to late adulthood. Multivariate analysis revealed strong relationships between these stable metrics within individuals, suggesting a complex behavioral syndrome comparable to human extraversion. Maternal effects (particularly vertical social learning) and sex-specific reproductive strategies are likely proximate and ultimate drivers for these patterns. We provide rare empirical evidence to demonstrate the persistence of social behavioral traits over decades in a non-human animal.

Tracing resilience, social dynamics and behavioral change: a review of agent-based flood risk models

Climate change and rapid urbanization exacerbate flood risks worldwide. The recognition of the crucial role that human actors play in altering risks and resilience of flood-prone cities triggers a paradigm shift in climate risks assessments and drives the proliferation of computational models that include societal dynamics. Yet, replacing a representative rational actor dominant in climate policy models with a variety of behaviorally-rich agents that interact, learn, and adapt is not straightforward. Focusing on the costliest climate-exacerbated hazard, flooding, we review computational agent-based models that include behavioral change and societal dynamics. We distinguish between two streams of literature: one stemming from economics & behavioral sciences and another from hydrology. Our findings show that most studies focus on households while representing decisions of other agents (government, insurance, urban developers) simplistically and entirely overlooking firms' choices in the face of risks. The two communities vary in the extent they ground agents' rules in social theories and behavioral data when modeling boundedly-rational decisions. While both aspire to trace feedbacks that agents collectively instigate, they employ different learning and interactions when computing societal dynamics in the face of climate risks. Dynamics of hazard, exposure, and vulnerability components of flood risks driven by incremental adaptation of agents are well represented. We highlight that applying a complex adaptive system perspective to trace the evolution of resilience can lead to a better understanding of transformational adaptation. The methodological advances in computational models with heterogeneous behaviorally-rich adaptive agents are relevant for adaptation to different climate-driven hazards beyond flooding.

Diseases don’t need passports: A life course approach to understanding high-risk sexual behaviors and attitudes among international travelers

ABSTRACT International travelers, who consist of a large proportion of the U.S. population, play a critical role in sustaining public health and homeland security. This study examined the life course and contextual factors that increased propensities for high-risk sexual behaviors and attitudes among international travelers. Forty-five frequent international travelers were recruited through purposive sampling to participate in an in-depth semi-structured interview to understand factors facilitating transmission of sexual health risks. Contrary to many quantitatively oriented travel and public health studies, this study was able to capture rich information (e.g., emotions, thought processing, decision-making process, context of risk) not easily available through traditional quantitative method of data collection (e.g., survey). Overall, study findings show that life transitions, factors weakening social control or self-control, and strengthening anonymity can promote a context that increases sexual exchanges between locals and travelers while abroad. This research calls for more public health, epidemiological, and social behavioral data that better depict the vulnerability that international travelers confront.

Score and Rank Level Fusion Algorithms for Social Behavioral Biometrics

The goal of a biometric system is to recognize individuals based on their unique physiological or behavioral traits. Online Social Networking (OSN) platforms have become an integral part of the daily life of individuals, where they leave a recognizable trail of behavioral information. Social Behavioral Biometric (SBB), being an emerging trend, focuses on such trails to distinguish between individuals. This research investigates the impact of users' writing profiles on OSN to conclude whether such profiles contribute to SBB. The distinctiveness of the SBB features that are extracted from the social behavioral data of Twitter is studied. A person identification system that relies on users' writing profiles, reply, retweet, shared weblink, trendy topic networks and temporal profiles is proposed. Score and rank level weighted fusion algorithm performance is compared on a social interaction database of 241 Twitter users. The experimental results establish that the users' writing profiles have the highest impact over other social biometric features and that score level fusion algorithms perform better than rank level fusion on SBB. The proposed system has achieved recognition rate of 99.45% at rank-1 after cross-validation using genetic algorithm based score level fusion algorithm. The system outperformed all prior researches on SBB in terms of identification accuracy.

A systematic review and evaluation of Zika virus forecasting and prediction research during a public health emergency of international concern.

IntroductionEpidemic forecasting and prediction tools have the potential to provide actionable information in the midst of emerging epidemics. While numerous predictive studies were published during the 2016–2017 Zika Virus (ZIKV) pandemic, it remains unknown how timely, reproducible, and actionable the information produced by these studies was.MethodsTo improve the functional use of mathematical modeling in support of future infectious disease outbreaks, we conducted a systematic review of all ZIKV prediction studies published during the recent ZIKV pandemic using the PRISMA guidelines. Using MEDLINE, EMBASE, and grey literature review, we identified studies that forecasted, predicted, or simulated ecological or epidemiological phenomena related to the Zika pandemic that were published as of March 01, 2017. Eligible studies underwent evaluation of objectives, data sources, methods, timeliness, reproducibility, accessibility, and clarity by independent reviewers.Results2034 studies were identified, of which n = 73 met the eligibility criteria. Spatial spread, R0 (basic reproductive number), and epidemic dynamics were most commonly predicted, with few studies predicting Guillain-Barré Syndrome burden (4%), sexual transmission risk (4%), and intervention impact (4%). Most studies specifically examined populations in the Americas (52%), with few African-specific studies (4%). Case count (67%), vector (41%), and demographic data (37%) were the most common data sources. Real-time internet data and pathogen genomic information were used in 7% and 0% of studies, respectively, and social science and behavioral data were typically absent in modeling efforts. Deterministic models were favored over stochastic approaches. Forty percent of studies made model data entirely available, 29% provided all relevant model code, 43% presented uncertainty in all predictions, and 54% provided sufficient methodological detail to allow complete reproducibility. Fifty-one percent of predictions were published after the epidemic peak in the Americas. While the use of preprints improved the accessibility of ZIKV predictions by a median of 119 days sooner than journal publication dates, they were used in only 30% of studies.ConclusionsMany ZIKV predictions were published during the 2016–2017 pandemic. The accessibility, reproducibility, timeliness, and incorporation of uncertainty in these published predictions varied and indicates there is substantial room for improvement. To enhance the utility of analytical tools for outbreak response it is essential to improve the sharing of model data, code, and preprints for future outbreaks, epidemics, and pandemics.

Clinical and Epidemiological Profile of Herpes Zoster; A Cross-Sectional Study from Tertiary Hospital

Background: Herpes zoster is dermatomal neuropathic disease caused by reactivation of varicella zoster virus, characterized by vesicobullous eruptions. Although, being a common cause of morbidity, there are few clinicepidemiological studies and the studies regarding the knowledge and practice among the patients are nominal.Methods: This was descriptive observational study which included 100 consecutive patients with herpes zoster who presented to Department of Dermatology and Venereology in a Teaching Hospital, Kathmandu during the period from July 2014 to June 2015.Results: The annual incidence was 0.55%. Seventy two percent were males and 28 percent were females with the M: F=2.5:1. The average age of patients and mean duration of disease was 40.4 years and 5.5 days respectively. Ninety five percent were managed at OPD and 5 % of them needed hospitalization. Most common dermatome involved was thoracic (50%) followed by cervical (20%). Twelve percent had one or more provocative features including diabetes, steroid use, chemotherapy, surgical trauma etc. Twenty patients had definite history chicken pox. Twenty-five percent had local complication at the time of presentation. Fifty two percent had themselves identified the lesion as herpes zoster. However, only 10 had some knowledge about it. Twelve percent had visited traditional healers prior to hospital arrival.Conclusions: The results show varied clinicoepidemiologic patterns of herpes zoster. Major patient have less knowledge about it. A larger study would be necessary for better clinical, epidemiological and social behavioral data. Because of ignorance and tradition, awareness program should be conducted to reduce potential complications. Med Phoenix. Vol. 3, Issue. 1, 2018, Page: 60-65

333 - Predicting Readmission Risk: A Promising Heart Failure Bedside Risk Stratification Tool

Introduction: Although many individual factors have been reported to worsen the prognosis of congestive heart failure (CHF) patients, it is challenging to build an accurate risk stratification tool for physicians and other health care providers to utilize at the point of care to identify patients at risk for readmissions. Limiting factors can include: correlations among reported prognostic factors; healthcare systems' lack of patients' social determinant and behavioral factor data; and difficulty embedding the risk stratification tools into healthcare providers' workflow. Hypothesis: We hypothesized that a model derived from a holistic conceptual framework of readmissions based on CHF's pathophysiology and prognosis would accurately stratify risk for readmissions among CHF patients. In addition, we hypothesized that a simple flowchart developed based on the risk model could suffice to facilitate bedside decisions when operationalizing a full predictive model into workflow was not feasible. Methods: Inpatient admissions with a primary discharge diagnosis of CHF from a large urban academic hospital between May 2013 and April 2016 were studied. A risk stratification model was derived and cross-validated from clinical and nonclinical factors to predict risk of 30-day unplanned all-cause readmission to the same facility. A flowchart was then developed based on the risk model. All data were extracted from electronic medical records and administrative data. Results: The 30-day readmission rate of the CHF study population was 15.23%. The model with 48 predictors demonstrated good discrimination (C statistic 0.77, 95% CI: 0.74 - 0.79) and calibration (Goodness-of-fit P = .8) for readmission. When using 0.15 (the prevalence rate) as the probability threshold for at-risk, the model resulted in a sensitivity of 0.74, specificity of 0.70, positive predictive value of 0.30, and negative predictive value of 0.94. Per the model, by reaching out to the patients with a predicted probability above the threshold (which was 38% of the patients discharged), we could capture 74% of the true readmissions. The flowchart containing only five factors demonstrated a reduced sensitivity, but similar specificity and predictive values as the model. Conclusions: Clinical and non-clinical factors derived from a holistic conceptual framework of readmissions demonstrated promising capability of accurately stratifying risk for readmissions among CHF patients. Risk stratification models may be simplified into a flowchart with acceptable reduction in performance to facilitate use at the point of care.

SILVERBACK+: scalable association mining via fast list intersection for columnar social data

We present Silverback+, a scalable probabilistic framework for accurate association rule and frequent item-set mining of large-scale social behavioral data. Silverback+ tackles the problem of efficient storage utilization and management via: (1) probabilistic columnar infrastructure and (2) using Bloom filters and sampling techniques. In addition, probabilistic pruning techniques based on Apriori method are developed, for accelerating the mining of frequent item-sets. The proposed target-driven techniques yield a significant reduction of the size of the frequent item-set candidates, as well as the required number of repetitive membership checks through a novel list intersection algorithm. Extensive experimental evaluations demonstrate the benefits of this context-aware consideration and incorporation of the infrastructure limitations when utilizing the corresponding research techniques. When compared to the traditional Hadoop-based approach for improving scalability by straightforwardly adding more hosts, Silverback+ exhibits a much better runtime performance, with negligible loss of accuracy.

Applying socioendocrinology to evolutionary models: fatherhood and physiology.

Owing to humans' unique life history pattern, particularly comparatively short interbirth intervals, early weaning, and prolonged support of multiple dependents, human females have greater reproductive value and higher lifetime fertility, on average, than do their Great Ape counterparts. As hominin females began weaning their young early and "stacking" dependents of various ages, they must have had cooperative allomaternal care partners already in place or been successful at concurrently soliciting help to ensure a high rate of survival of their offspring. Following Hrdy, I define allomaternal care (and its derivatives, such as "allomothers" and "allomothering") as "care from anyone other than the mother," which thus encompasses a wide range of individuals, including fathers. Who the likely allomother candidates mothers were and what form that cooperation took remain intriguing, difficult-to-answer questions, which are limited, in some capacity, by the lines of evidence available to us. Here, I present a framework for the ways in which we can integrate neurobiological-endocrine and social-behavioral data ("socioendocrinology") to contribute to this dialogue in terms of evaluating fathers' roles.

Population based cohort study for pediatric infectious diseases research in Vietnam.

A population-based cohort study on pediatric infectious diseases was established at Khanh Hoa Province, central Vietnam in 2006, to determine the etiology and risk factors for severe pediatric infectious diseases (SPID) such as acute respiratory infection (ARI), diarrhea and dengue which are the major causes of under 5 mortality. A population census survey was conducted in Nha-Trang and Ninh-Hoa to collect demographic, social-behavioral data and disease burden on SPID. The study site covered a population of 353,525 residing in 75,826 households with 24,781 children less than 5 years. Hospital databases from two hospitals covering the region were obtained. Linking the census and hospital databases, we were able to investigate on a variety of SPID such as environmental tobacco smoking exposure and increased risked of pediatric pneumonia hospitalization, population density, water supply and risk of dengue fever and animal livestock and risk of hospitalized diarrhea. To determine incidence, viral etiology and risk factors for pediatric ARI/pneumonia, we setup a population based prospective hospitalized Pediatric ARI surveillance at Khanh Hoa General Hospital, Nha-Trang in February 2007. The study has revealed RSV, rhinovirus and influenza A as major viral pathogens, role of multiple viral infection and its interaction with bacteria in the development of pneumonia. In addition, we are also conducting a birth cohort study to investigate the incidence of congenital infection and its impact on physical-neurological development, and role of host genetic polymorphism on SPID hospitalization in Vietnam. Population mobility, high cost of regular census update and low mortality are the challenges.

A role for the superior colliculus in the modulation of threat responsiveness in primates: toward the ontogenesis of the social brain

Defense and social mechanisms in primates seem to share, at least in infancy, common neural substrata.Among these, recent research has implicated the primate superior colliculus (SC) on tasks involving visual detection and recognition of threatening stimuli, such as snakes and faces with emotional expressions. There is also evidence that both kinds of stimuli share specific characteristics and command special attention in the primate visual system. The present review focuses on the role of the SC in these seemingly overlapping functions.We present social behavioral data from capuchin monkeys in which the bilateral lesion of the SC induced a transitory impairment of social behaviors. The findings presented here are compared with previous studies, our own and others, on social behaviors and threat detection. We argue that, although the SC may participate in both systems,its role is more prominent in the detection/recognition of threat. Social interactions more likely depend on larger and more complex neural systems, where the SC may play a key role in early infancy. The implications of these recent findings are discussed under an evolutionary perspective.

Social Learning

In recent years, social behavioral data have been exponentially expanding due to the tremendous success of various outlets on the social Web (aka Web 2.0) such as Facebook, Digg, Twitter, Wikipedia, and Delicious. As a result, there's a need for social learning to support the discovery, analysis, and modeling of human social behavioral data. The goal is to discover social intelligence, which encompasses a spectrum of knowledge that characterizes human interaction, communication, and collaborations. The social Web has thus become a fertile ground for machine learning and data mining research. This special issue gathers the state-of-the-art research in social learning and is devoted to exhibiting some of the best representative works in this area.