How to Improve Compliance with Protective Health Measures During the Covid-19 Outbreak: Testing a Moderated Mediation Model and Machine Learning Algorithms (Preprint)

2020 ◽  
Author(s):  
Cristina Mazza ◽  
Merylin Monaro ◽  
Laura Muzi ◽  
Marco Colasanti ◽  
Eleonora Ricci ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Perception ◽  
Civic Engagement ◽  
Moderated Mediation ◽  
Machine Learning Algorithms ◽  
Perceived Efficacy ◽  
Protective Measures ◽  
Behavioral Compliance ◽  
Civic Attitudes ◽  
Health Measures

BACKGROUND In the wake of the sudden spread of COVID-19, much of the Italian population practiced behaviors that were incongruous with the protective health measures promoted by the Italian government. OBJECTIVE The present study aimed at examining psychological and psychosocial variables that could potentially predict behavioral compliance. METHODS An online survey was administered from 18–22 March 2020. There were 2,766 participants (71.7% female, 28.3% male), with an average age of 32.94 years (SD = 13.2; range 18–90 years). Paired sample t-tests were run to compare efficacy perception with behavioral compliance. Mediation and moderated mediation models were constructed to explore the association between perceived efficacy and compliance, mediated by self-efficacy and moderated by risk perception and civic attitudes. Machine learning algorithms were trained on all of the collected psychosocial variables to predict which individuals would be more likely to comply with COVID-19 protective measures. RESULTS The results indicated significantly lower scores in behavioral compliance (M = 41.7, SD = 6.20) relative to efficacy perception (M = 44.8, SD = 6.17). The introduction of risk perception and civic attitudes as moderators rendered the mediating effect of self-efficacy insignificant. The impact of perceived efficacy on the adoption of recommended behaviors varied in accordance with risk perception and civic engagement. The best pool of predictors (15 out of 199), identified using the correlation-based feature selector, produced a ROC area in the range of 0.83–0.93 for classifying individuals as high versus low compliance. CONCLUSIONS Government awareness communications and campaigns regarding COVID-19 and related protective measures should be tailored to specific segments of the population, as defined by age and level of education. Furthermore, they should emphasize the efficacy of the recommended measures in successfully preventing the virus spread. Finally, they should take into account risk perception and should highlight the importance of civic engagement. CLINICALTRIAL N/A

scholarly journals How to Improve Compliance with Protective Health Measures during the COVID-19 Outbreak: Testing a Moderated Mediation Model and Machine Learning Algorithms

2020 ◽  
Vol 17 (19) ◽  
pp. 7252 ◽  
Author(s):  
Paolo Roma ◽  
Merylin Monaro ◽  
Laura Muzi ◽  
Marco Colasanti ◽  
Eleonora Ricci ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Perception ◽  
Self Efficacy ◽  
Learning Algorithms ◽  
Moderated Mediation ◽  
Machine Learning Algorithms ◽  
Perceived Efficacy ◽  
Behavioral Compliance ◽  
Civic Attitudes ◽  
Health Measures

In the wake of the sudden spread of COVID-19, a large amount of the Italian population practiced incongruous behaviors with the protective health measures. The present study aimed at examining psychological and psychosocial variables that could predict behavioral compliance. An online survey was administered from 18–22 March 2020 to 2766 participants. Paired sample t-tests were run to compare efficacy perception with behavioral compliance. Mediation and moderated mediation models were constructed to explore the association between perceived efficacy and compliance, mediated by self-efficacy and moderated by risk perception and civic attitudes. Machine learning algorithms were trained to predict which individuals would be more likely to comply with protective measures. Results indicated significantly lower scores in behavioral compliance than efficacy perception. Risk perception and civic attitudes as moderators rendered the mediating effect of self-efficacy insignificant. Perceived efficacy on the adoption of recommended behaviors varied in accordance with risk perception and civic engagement. The 14 collected variables, entered as predictors in machine learning models, produced an ROC area in the range of 0.82–0.91 classifying individuals as high versus low compliance. Overall, these findings could be helpful in guiding age-tailored information/advertising campaigns in countries affected by COVID-19 and directing further research on behavioral compliance.

The Effects of COVID-19 Infection Cues on Preventive Behaviors: Development of a Moderated Mediation Model (Preprint)

2021 ◽  
Author(s):  
Guangteng Meng ◽  
Xiaoyan Yuan ◽  
Qi Li ◽  
Bibing Dai ◽  
Xun Liu
Keyword(s):  
Risk Perception ◽  
Online Survey ◽  
Negative Emotions ◽  
Moderated Mediation ◽  
Self Report ◽  
Preventive Behaviors ◽  
Cross Sectional ◽  
Perceived Efficacy ◽  
Moderated Mediation Model ◽  
Nationally Representative

BACKGROUND The coronavirus disease 2019 (COVID-19) pandemic has disrupted the lives of everyone worldwide. Prevention behaviors are especially critical to protect the people who have patients around; however, little work has been done to explore the influences of infection cues on preventive behaviors. OBJECTIVE The purpose of this study was to explore the influence of infection cues on preventive behaviors and the roles of risk perception, negative emotions, and perceived efficacy in this influence. METHODS A cross-sectional online survey with a nationally representative sample in China was conducted during the first wave of COVID-19 in China. Self-report measures of infection cues, preventive behaviors, risk perception, negative emotions, and perceived efficacy. The PROCESS macro (Model 85) was used to test our conceptual model. RESULTS A total of 26511 participants responded to the survey and 20205 valid responses (76.2%) were obtained for further analysis. Moderated mediation results show that infection cues positively predicted preventive behaviors and in turn affected preventive behaviors through risk perception and negative emotions. Moreover, perceived efficacy moderated the influence of infection cues not only on preventive behaviors but also on risk perception and negative emotions related to preventive behaviors. The higher the perceived efficacy, the stronger these influences were. CONCLUSIONS This study revealed that infection cues promoted preventive behaviors by increasing risk perception and negative emotions and that high perceived efficacy further enhanced these effects.

scholarly journals A machine learning tool for interpreting differences in cognition using brain features

2019 ◽  
Author(s):  
Tiago Azevedo ◽  
Luca Passamonti ◽  
Pietro Lió ◽  
Nicola Toschi
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Machine Learning Algorithms ◽  
Public Repository ◽  
Cognitive Differences ◽  
Health Measures ◽  
Human Connectome Project ◽  
Neuroimaging Data ◽  
Recent Developments ◽  
Surface Based Morphometry

AbstractPredicting variability in cognition traits is an attractive and challenging area of research, where different approaches and datasets have been implemented with mixed results. Some powerful Machine Learning algorithms employed before are difficult to interpret, while other algorithms are easy to interpret but might not be as powerful. To improve understanding of individual cognitive differences in humans, we make use of the most recent developments in Machine Learning in which powerful prediction models can be interpreted with confidence. We used neuroimaging data and a variety of behavioural, cognitive, affective and health measures from 905 people obtained from the Human Connectome Project (HCP). As a main contribution of this paper, we show how one could interpret the neuroanatomical basis of cognition, with recent methods which we believe are not yet fully explored in the field. By reducing neuroimages to a well characterised set of features generated from surface-based morphometry and cortical myelin estimates, we make the interpretation of such models easier as each feature is self-explanatory. The code used in this tool is available in a public repository: https://github.com/tjiagoM/interpreting-cognition-paper-2019

scholarly journals Intolerance of COVID-19-Related Uncertainty and Negative Emotions among Chinese Adolescents: A Moderated Mediation Model of Risk Perception, Social Exclusion and Perceived Efficacy

2021 ◽  
Vol 18 (6) ◽  
pp. 2864
Author(s):  
Qi Li ◽  
Ronglei Luo ◽  
Xiaoya Zhang ◽  
Guangteng Meng ◽  
Bibing Dai ◽  
...  
Keyword(s):  
Risk Perception ◽  
Social Exclusion ◽  
Negative Emotions ◽  
Moderated Mediation ◽  
Mediating Effect ◽  
Mediation Model ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
Perceived Efficacy ◽  
Moderated Mediation Model

The uncertainty caused by the COVID-19 pandemic has exacerbated negative emotions, especially among adolescents, who feel unable to tolerate the uncertainty of the epidemic. However, the mechanism by which the intolerance of COVID-19-related uncertainty (COVID-19 IU) affects negative emotions in adolescents remains unclear. This study explored the underlying mechanism from COVID-19 IU to negative emotions using a moderated mediation model in adolescents. In total, 3037 teenagers completed a cross-sectional survey including measures of COVID-19 IU, risk perception, social exclusion, perceived efficacy, and negative emotions. The results showed that COVID-19 IU positively predicted negative emotions and that risk perception and social exclusion mediated this relationship. In addition, both the direct effect of COVID-19 IU on negative emotions and the mediating effect of risk perception on this relationship were moderated by perceived efficacy; in particular, COVID-19 IU had a greater impact on negative emotions among adolescents with lower levels of perceived efficacy. These findings suggest that COVID-19 IU is closely associated with negative emotions among adolescents and that effective measures should be taken to enable adolescents to improve their perceived efficacy and develop a reasonable perception of risk, help them eliminate the stigma of the disease, and strengthen their connections with society.

scholarly journals Prediction and Diagnosis of COVID-19 using Machine Learning Algorithms

2020 ◽  
Vol 9 (3) ◽  
pp. 678-683
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Noisy Data ◽  
Machine Learning Algorithms ◽  
Risk Assessments ◽  
Resting Heart Rate ◽  
The Core ◽  
Health Measures ◽  
Digital Era ◽  
The World

The world is reworking in a digital era. However, the field of medicine was quite repulsive to technology. Recently, the advent of newer technologies like machine learning has catalyzed its adoption into healthcare. The blending of technology and medicine is facilitating a wealth of innovation that continues to improve lives. With the realm of possibility, machine learning is discovering various trends in a dataset and it is globally practiced in various medical conditions to predict the results, diagnose, analyze, treat, and recover. Machine Learning is aiding a lot to fight the battle against Covid-19. For instance, a face scanner that uses ML is used to detect whether a person has a fever or not. Similarly, the data from wearable technology like Apple Watch and Fitbit can be used to detect the changes in resting heart rate patterns which help in detecting coronavirus. According to a study by the Hindustan Times, the number of cases is rapidly increasing. Careful risk assessments should identify hotspots and clusters, and continued efforts should be made to further strengthen capacities to respond, especially at sub-national levels. The core public health measures for the Covid-19 response remain, rapidly detect, test, isolate, treat, and trace all contacts. The work presented in this paper represents the system that predicts the number of coronavirus cases in the upcoming days as well as the possibility of the infection in a particular person based on the symptoms. The work focuses on Linear Regression and SVM models for predicting the curve of active cases. SVM is least affected by noisy data, and it is not prone to overfitting. To diagnose a person our application has a certain question that needs to be answered. Based on this, the KNN model provides the maximum likelihood result of a person being infected or not. Tracking and monitoring in the course of such pandemic help us to be prepared.

scholarly journals Explainable death toll motion modeling: COVID-19 narratives and counterfactuals

2020 ◽  
Author(s):  
Adriano Veloso ◽  
Nivio Ziviani
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Machine Learning Algorithms ◽  
Data Driven ◽  
Motion Modeling ◽  
Motion Models ◽  
Health Measures ◽  
Death Toll ◽  
Country Level ◽  
Acceleration Model

Models have gained the spotlight in many discussions surrounding COVID-19. The urgency for timely decisions resulted in a multitude of models as informed policy actions must be made even when so many uncertainties about the pandemic still remain. In this paper, we use machine learning algorithms to build intuitive country-level COVID-19 motion models described by death toll velocity and acceleration. Model explainability techniques provide insightful data-driven narratives about COVID-19 death toll motion models $-$ while velocity is explained by factors that are increasing/reducing death toll pace now, acceleration anticipates the effects of public health measures on slowing the death toll pace. This allows policymakers and epidemiologists to understand factors driving the outbreak and to evaluate the impacts of different public health measures. Finally, our models also predict counterfactuals in order to face the challenge of estimating what is likely to happen as a result of an action.

The Roles of Risk Perception, Negative Emotions and Perceived Efficacy in the Association Between COVID-19 Infection Cues and Preventive Behaviors: A Moderated Mediation Model (Preprint)

2021 ◽  
Author(s):  
Guangteng Meng ◽  
Xiaoyan Yuan ◽  
Ya Zheng ◽  
Kesong Hu ◽  
Qi Li ◽  
...  
Keyword(s):  
Risk Perception ◽  
Online Survey ◽  
Negative Emotions ◽  
Moderated Mediation ◽  
Preventive Behaviors ◽  
Promoting Effect ◽  
Cross Sectional ◽  
Perceived Efficacy ◽  
Moderated Mediation Model ◽  
Action Model

BACKGROUND The coronavirus disease 2019 (COVID-19) pandemic has disrupted the lives of everyone worldwide. Preventive behaviors are especially critical to the protection of individuals whose family members or acquaintances have been infected. However, limited research has explored the influence of infection cues on preventive behaviors. OBJECTIVE This study proposed the information-perception/emotion-action model (IPEAM) to elucidate the mechanism by which infection cues influence preventive behaviors and the roles of risk perception, negative emotions, and perceived efficacy in that influence. METHODS A cross-sectional online survey was conducted in 34 provinces in China during the first wave of the COVID-19 pandemic. A moderated mediation analysis was conducted to examine whether risk perception and negative emotions mediated and perceived efficacy moderated the relationship between infection cues and preventive behaviors. RESULTS A total of 26511 participants responded to the survey and 20205 valid responses (76.2%) were obtained for further analysis. The moderated mediation results show that infection cues positively predicted preventive behaviors in a manner mediated by risk perception (Bindirect=0.135, 95% CI 0.118 to 0.153) and negative emotions (Bindirect=0.140, 95% CI 0.122 to 0.159). Moreover, perceived efficacy moderated the influence of infection cues not only on preventive behaviors (B=0.013, P=.01) but also on risk perception (B=0.130, P<.001) and negative emotions (B=0.232, P<.001). The higher the perceived efficacy, the stronger these influences were. CONCLUSIONS These findings validated our IPEAM, which elucidates the mechanisms underlying the promoting effect of infection cues on preventive behaviors during the initial stage of the COVID-19 pandemic. This study suggests that governments should establish early warning and support systems based on the dynamic surveillance of infection cues. INTERNATIONAL REGISTERED REPORT RR2-28986

Forecasting US movies box office performances in Turkey using machine learning algorithms

2020 ◽  
Vol 39 (5) ◽  
pp. 6579-6590
Author(s):  
Sandy Çağlıyor ◽  
Başar Öztayşi ◽  
Selime Sezgin
Keyword(s):  
Machine Learning ◽  
Global Economy ◽  
Learning Algorithms ◽  
Forecast Model ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
High Stakes ◽  
Box Office ◽  
Industry Forecast ◽  
The Impact

The motion picture industry is one of the largest industries worldwide and has significant importance in the global economy. Considering the high stakes and high risks in the industry, forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at the early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study, the aim is to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey. From various sources, a dataset of 1559 movies is constructed. Firstly, independent variables are grouped as pre-release, distributor type, and international distribution based on their characteristic. The number of attendances is discretized into three classes. Four popular machine learning algorithms, artificial neural networks, decision tree regression and gradient boosting tree and random forest are employed, and the impact of each group is observed by compared by the performance models. Then the number of target classes is increased into five and eight and results are compared with the previously developed models in the literature.

Intelligent system of English composition scoring model based on improved machine learning algorithm

2020 ◽  
pp. 1-11
Author(s):  
Jie Liu ◽  
Lin Lin ◽  
Xiufang Liang
Keyword(s):  
Machine Learning ◽  
Evaluation System ◽  
Intelligent System ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Assessment System ◽  
English Composition ◽  
Region Extraction ◽  
Constraint Model

The online English teaching system has certain requirements for the intelligent scoring system, and the most difficult stage of intelligent scoring in the English test is to score the English composition through the intelligent model. In order to improve the intelligence of English composition scoring, based on machine learning algorithms, this study combines intelligent image recognition technology to improve machine learning algorithms, and proposes an improved MSER-based character candidate region extraction algorithm and a convolutional neural network-based pseudo-character region filtering algorithm. In addition, in order to verify whether the algorithm model proposed in this paper meets the requirements of the group text, that is, to verify the feasibility of the algorithm, the performance of the model proposed in this study is analyzed through design experiments. Moreover, the basic conditions for composition scoring are input into the model as a constraint model. The research results show that the algorithm proposed in this paper has a certain practical effect, and it can be applied to the English assessment system and the online assessment system of the homework evaluation system algorithm system.

Sign in / Sign up

Export Citation Format

Share Document