A Comprehensive Analysis of Clustering Public Utility Bus Passenger's Behavior during the COVID-19 Pandemic: Utilization of Machine Learning with Metaheuristic Algorithm

Public utility bus (PUB) systems and passenger behaviors drastically changed during the COVID-19 pandemic. This study assessed the clustered behavior of 505 PUB passengers using feature selection, K-means clustering, and particle swarm optimization (PSO). The wrapper method was seen to be the best among the six feature selection techniques through recursive feature selection with a 90% training set and a 10% testing set. It was revealed that this technique produced 26 optimal feature subsets. These features were then fed into K-means clustering and PSO to find PUB passengers' clusters. The algorithm was tested using 12 different parameter settings to find the best outcome. As a result, the optimal parameter combination produced 23 clusters. Utilizing the Pareto analysis, the study only considered the vital clusters. Specifically, five vital clusters were found to have comprehensive similarities in demographics and feature responses. The PUB stakeholders could use the cluster findings as a benchmark to improve the current system.

Online or Traditional Learning at the Near End of the Pandemic: Assessment of Students' Intentions to Pursue Online Learning in the Philippines

Online learning has been utilized due to the sudden shift taken among educational institutions to continue students' learning during the COVID-19 pandemic. Three years into the pandemic, universities now offer different modalities of education due to the establishment of online and modular learning modalities. Hence, the intention of students to adapt to online learning despite the availability of traditional learning is underexplored. With the limited availability of face-to-face learning at the near end of the epidemic in the Philippines, this study sought to analyze the factors that influenced behavioral intentions towards continuing online learning modalities. Five hundred students from different universities in the Philippines participated and answered 42 adapted questions in an online survey via Google Forms. Structural equation modeling (SEM) was used in this study, with factors such as an affective latent variable, attitude towards behavior, autonomy, relatedness, competency, expectation, confirmation, satisfaction, and behavioral intention. The study found that attitude towards behavior has the highest positive direct effect on students' intentions to pursue online learning, followed by expectation and confirmation, satisfaction and behavioral intention, competence and behavioral intention, and the affective variable and satisfaction. The effect of expectations on satisfaction and the affective variable on behavioral intentions was seen to have no significance regarding students' intentions. This also study integrated expectation–confirmation theory, the theory of planned behavior, and self-determination theory to holistically evaluate students' intentions to pursue online learning despite the availability of traditional learning. The educational sector can utilize these findings to consider pursuing and offering online learning. Additionally, the study can help future researchers evaluate students' behavioral intentions concerning online learning.

Factors Influencing the Perceived Effectiveness of COVID-19 Risk Assessment Mobile Application “MorChana” in Thailand: UTAUT2 Approach

COVID-19 contact-tracing mobile applications have been some of the most important tools during the COVID-19 pandemic. One preventive measure that has been incorporated to help reduce the virus spread is the strict implementation of utilizing a COVID-19 tracing application, such as the MorChana mobile application of Thailand. This study aimed to evaluate the factors affecting the actual usage of the MorChana mobile application. Through the integration of Protection Motivation Theory (PMT) and Unified Theory of Acceptance and Use of Technology (UTAUT2), latent variables such as performance expectancy (PE), effort expectancy (EE), social influence (SI), facilitating conditions (FC), hedonic motivation (HM), habit (HB), perceived risk (PCR), self-efficacy (SEF), privacy (PR), trust (TR), and understanding COVID-19 (U) were considered to measure the intention to use MorChana (IU) and the actual usage (AU) of the mobile application. This study considered 907 anonymous participants who voluntarily answered an online self-administered survey collected via convenience sampling. The results show that IU presented the highest significant effect on AU, followed by HB, HM, PR, FC, U, SEF, PE, EE, TR, and SI. This is evident due to the strict implementation of using mobile applications upon entering any area of the vicinity. Moreover, PCR was not seen to be a significant latent factor affecting AU. This study is the first to have evaluated mobile contact tracing in Thailand. The integrated framework can be applied and extended to determine factors affecting COVID-19 tracing applications in other countries. Moreover, the findings of this study could be applied to other health-related mobile applications worldwide.