Utilization of Random Forest and Deep Learning Neural Network for Predicting Factors Affecting Perceived Usability of a COVID-19 Contact Tracing Mobile Application in Thailand "ThaiChana"

Predicting factors influencing perceived online learning experience among primary students utilizing structural equation modeling Forest Classifier approach

Introduction

Amid the COVID-19 pandemic, the temporary closure of educational institutions led to the adoption of remote or online learning delivery. Challenges, especially for grade schools were evident.

Objective

This study aimed to identify factors affecting the perceived online discussion experience of Filipino primary students through distance learning in the National Capital Region, Philippines.

Method

Variables such as cognitive presence, teaching presence, social presence, and online discussion experience were investigated simultaneously by utilizing the structural equation modeling (SEM) and random forest classifier (RFC) approach. A total of 385 currently enrolled Filipino grade school student participants were surveyed.

Results

Results show that cognitive presence has the most significant impact on the perceived online discussion experience, followed by teaching presence, and social presence. This study is the first study that analyzed the online discussion experience among grade school students in online education in the Philippines considering SEM and RFC. It was seen that highly significant factors such as teaching presence, cognitive presence, social presence, triggering events, and exploration will lead to high and very high learning experience with grade school students.

Conclusion

The findings of this study would be significant for teachers, educational institutions, and government agencies to improve the online delivery of primary education in the country. In addition, this study presents a reliable model and results which can be extended and applied for academicians, educational institutions, and the education sector to develop ways in enhancing the online delivery of primary education worldwide.

Classification modeling of intention to donate for victims of Typhoon Odette using deep learning neural network

The need for stability in the economy for world development has been a challenge due to the COVID-19 pandemic. In addition, the increase of natural disasters and their aftermath have been increasing causing damages to infrastructure, the economy, livelihood, and lives in general. This study aimed to determine factors affecting the intention to donate for victims of Typhoon Odette, a recent super typhoon that hit the Philippines leading to affect 38 out of 81 provinces of the most natural disaster-prone countries. Determining the most significant factor affecting the intention to donate may help in increasing the engagement of donations among other people to help establish a more stable economy to heighten world development. With the use of deep learning neural network, a 97.12% accuracy was obtained for the classification model. It could be deduced that when donors understand and perceive both severity and vulnerability to be massive and highly damaging, then a more positive intention to donate to victims of typhoons will be observed. In addition, the influence of other people, the holiday season when the typhoon happened, and the media as a platform have greatly contributed to heightening the intention to donate and control over the donor's behavior. The findings of this study could be applied and utilized by government agencies and donation platforms to help engage and promote communication among donors. Moreover, the framework and methodology considered in this study may be extended to evaluate intention, natural disasters, and behavioral studies worldwide.

Machine Learning and COVID-19: Lessons from SARS-CoV-2

Currently, methods in machine learning have opened a significant number of applications to construct classifiers with capacities to recognize, identify, and interpret patterns hidden in massive amounts of data. This technology has been used to solve a variety of social and health issues against coronavirus disease 2019 (COVID-19). In this chapter, we present some supervised and unsupervised machine learning techniques that have contributed in three aspects to supplying information to health authorities and diminishing the deadly effects of the current worldwide outbreak on the population. First is the identification and construction of powerful classifiers capable of predicting severe, moderate, or asymptomatic responses in COVID-19 patients starting from clinical or high-throughput technologies. Second is the identification of groups of patients with similar physiological responses to improve the triage classification and inform treatments. The final aspect is the combination of machine learning methods and schemes from systems biology to link associative studies with mechanistic frameworks. This chapter aims to discuss some practical applications in the use of machine learning techniques to handle data coming from social behavior and high-throughput technologies, associated with COVID-19 evolution.

Predicting factors affecting the intention to use a 3PL during the COVID-19 pandemic: A machine learning ensemble approach

The COVID-19 pandemic had brought changes to individuals, especially in consumer behavior. As the government of different countries has been implementing safety protocols to mitigate the spread of the virus, people became apprehensive about traveling and going out. This paved way for the emergence of third-party logistics (3PL). Statistics have proven the rapid escalation regarding the use of 3PL in various countries. This study utilized Artificial Neural Network and Random Forest Classifier to validate and justify the factors that affect consumer intention in selecting a 3PL service provider during the COVID-19 pandemic integrating the Service Quality Dimensions and Pro-Environmental Theory of Planned Behavior. The findings of this study revealed that attitude is the most significant factor that affects the consumers' behavioral intention. Other factors such as customer satisfaction, customer perceived value, perceived environmental concern, assurance, responsiveness, empathy, reliability, tangibility, perceived behavioral control, subjective norm, and perceived authority support, are all contributing factors that affect behavioral intention. Machine learning algorithms, specifically ANN and RFC, resulted to be reliable in predicting factors as they obtained accuracy rates of 98.56% and 93%. Results presented that consumers’ attitude, satisfaction, perceived value, assurance by the 3PL, and perceived environmental concerns were highly influential in choosing a 3PL package carrier. It was seen that people would be encouraged to use 3PL service providers if they demonstrate availability and environmental concerns in catering to the customers' needs. Subsequently, 3PL providers must assure safety and convenience before, during, and after providing the service to ensure continuous patronage of consumers. This is considered to be the first study that utilized a machine learning ensemble to measure behavioral intention for the logistic sector. The framework, analysis tools, and findings of this study could be extended and applied among other behavioral intentions regarding transportation worldwide. Managerial insights among service providers are discussed.

Utilization of Random Forest Classifier and Artificial Neural Network for Predicting Factors Influencing the Perceived Usability of COVID-19 Contact Tracing “MorChana” in Thailand

With the constant mutation of COVID-19 variants, the need to reduce the spread should be explored. MorChana is a mobile application utilized in Thailand to help mitigate the spread of the virus. This study aimed to explore factors affecting the actual use (AU) of the application through the use of machine learning algorithms (MLA) such as Random Forest Classifier (RFC) and Artificial Neural Network (ANN). An integrated Protection Motivation Theory (PMT) and the Unified Theory of Acceptance and Use of Technology (UTAUT) were considered. Using convenience sampling, a total of 907 valid responses from those who answered the online survey were voluntarily gathered. With 93.00% and 98.12% accuracy from RFC and ANN, it was seen that hedonic motivation and facilitating conditions were seen to be factors affecting very high AU; while habit and understanding led to high AU. It was seen that when people understand the impact and causes of the COVID-19 pandemic’s aftermath, its severity, and also see a way to reduce it, it would lead to the actual usage of a system. The findings of this study could be used by developers, the government, and stakeholders to capitalize on using the health-related applications with the intention of increasing actual usage. The framework and methodology used presented a way to evaluate health-related technologies. Moreover, the developing trends of using MLA for evaluating human behavior-related studies were further justified in this study. It is suggested that MLA could be utilized to assess factors affecting human behavior and technology used worldwide.

Utilizing Structural Equation Modeling-Artificial Neural Network Hybrid Approach in Determining Factors Affecting Perceived Usability of Mobile Mental Health Application in the Philippines

Mental health problems have emerged as one of the biggest problems in the world and one of the countries that has been seen to be highly impacted is the Philippines. Despite the increasing number of mentally ill Filipinos, it is one of the most neglected problems in the country. The purpose of this study was to determine the factors affecting the perceived usability of mobile mental health applications. A total of 251 respondents voluntarily participated in the online survey we conducted. A structural equation modeling and artificial neural network hybrid was applied to determine the perceived usability (PRU) such as the social influence (SI), service awareness (SA), technology self-efficacy (SE), perceived usefulness (PU), perceived ease of use (PEOU), convenience (CO), voluntariness (VO), user resistance (UR), intention to use (IU), and actual use (AU). Results indicate that VO had the highest score of importance, followed by CO, PEOU, SA, SE, SI, IU, PU, and ASU. Having the mobile application available and accessible made the users perceive it as highly beneficial and advantageous. This would lead to the continuous usage and patronage of the application. This result highlights the insignificance of UR. This study was the first study that considered the evaluation of mobile mental health applications. This study can be beneficial to people who have mental health disorders and symptoms, even to health government agencies. Finally, the results of this study could be applied and extended among other health-related mobile applications worldwide.