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”

Abstract

The continuous rise of the COVID-19 Omicron cases despite the vaccination program available has been progressing worldwide. To mitigate the COVID-19 contraction, different contact tracing applications have been utilized such as Thai Chana from Thailand. This study aimed to predict factors affecting the perceived usability of Thai Chana by integrating the Protection Motivation Theory and Technology Acceptance Theory considering the System Usability Scale, utilizing deep learning neural network and random forest classifier. A total of 800 respondents were collected through convenience sampling to measure different factors such as understanding COVID-19, perceived severity, perceived vulnerability, perceived ease of use, perceived usefulness, attitude towards using, intention to use, actual system use, and perceived usability. In total, 97.32% of the deep learning neural network showed that understanding COVID-19 presented the most significant factor affecting perceived usability. In addition, random forest classifier produced a 92% accuracy with a 0.00 standard deviation indicating that understanding COVID-19 and perceived vulnerability led to a very high perceived usability while perceived severity and perceived ease of use also led to a high perceived usability. The findings of this study could be considered by the government to promote the usage of contact tracing applications even in other countries. Finally, deep learning neural network and random forest classifier as machine learning algorithms may be utilized for predicting factors affecting human behavior in technology or system acceptance worldwide.

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

“…Since MLAs were developed in accordance with statistical tools, it was seen that the consideration of MLA as an alternative tool to replace traditional statistical analysis has been the trend [44]. With the presented studies [21][22][23]42,43], it could be deduced that higher accuracy for the classification model would be obtained for RFC as compared to the basic decision tree. In addition, other classification tools are also available such as different types of regression.…”

“…To which, an extension of the study utilizing MLA ensembles such as neural network and RFC was conducted to highlight the most influential factor. The results of the extended study were seen to highlight the perception of severity and how perceived ease of use affected the perceived usability of the mobile application [42]. The study posited that using an MLA ensemble would be beneficial in directly identifying factors affecting perceived usability and actual use due to the limitations set by multivariate tools such as SEM.…”

“…Machine learning algorithms are of different types, wherein classification tools are commonly utilized for pattern recognition. It was stated from the study by Ong et al [42,43] how MLAs such as RFC and ANN have been recognized in the field of human factors to evaluate human behavior. However, Jamshidi et al [44] highlighted that the use of artificial intelligence and machine learning can be debatable when it comes to their application since their use is highly dependent on human input, the role of the individual, and collaboration in the roles of human.…”

“…Other classification models could be compared to it, such as K-Nearest Neighbor and Naïve Bayes. However, Ong et al [42] explained how these classification models are more complex and would be applicable for more complex frameworks. Lastly, clustering algorithms such as K-Means may also be considered, that is if the aim of the study is to create groupings of indicators or items affecting a dependent variable.…”

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

“…In addition, the inclusion of other factors may be considered to assess the usability of mental health applications. Fourth, it is suggested that methodology focusing solely on machine learning algorithm is considered in order to assess the claims found in several studies focusing on consumer behavior [ 64 ] and technology usability [ 65 ]. Lastly, differentiation based on demographics was not conducted.…”