How information and communication overload affect consumers' platform switching behavior in social commerce.

In social commerce, users are increasingly resorting to social media platforms to search for information, purchase goods, and share shopping experiences. However, social media use may also affect users' emotions negatively, causing them to switch platforms. Therefore, this study aims to investigate how negative factors (i.e., information and communication overload) affect consumers' platform-switching behavior in social commerce. Drawing on the stimulus-organism-response (SOR) model, this study established a research framework and conducted an online survey in China. A purposive sampling technique was used to collect the data, generating 477 valid responses. Data analysis, based on structural equation modeling, indicates that information and communication overload, and online fatigue positively affect platform-switching intention. The effect of the intention to switch on behavior is moderated by switching costs. Mediation analysis shows that information and communication overload can indirectly influence switching behavior through online fatigue and switching intention. This study incorporates the novel aspects of switching costs in examining the driving forces behind platform-switching in social commerce, thereby theoretically adding value to the existing body of knowledge. Apart from this, our findings also bear significant practical implications and are valuable for social commerce platforms and sellers to improve their user experience and retain existing customers.

An Explainable Student Fatigue Monitoring Module with Joint Facial Representation.

Online fatigue estimation is, inevitably, in demand as fatigue can impair the health of college students and lower the quality of higher education. Therefore, it is essential to monitor college students' fatigue to diminish its adverse effects on the health and academic performance of college students. However, former studies on student fatigue monitoring are mainly survey-based with offline analysis, instead of using constant fatigue monitoring. Hence, we proposed an explainable student fatigue estimation model based on joint facial representation. This model includes two modules: a spacial-temporal symptom classification module and a data-experience joint status inferring module. The first module tracks a student's face and generates spatial-temporal features using a deep convolutional neural network (CNN) for the relevant drivers of abnormal symptom classification; the second module infers a student's status with symptom classification results with maximum a posteriori (MAP) under the data-experience joint constraints. The model was trained on the benchmark NTHU Driver Drowsiness Detection (NTHU-DDD) dataset and tested on an Online Student Fatigue Monitoring (OSFM) dataset. Our method outperformed the other methods with an accuracy rate of 94.47% under the same training-testing setting. The results were significant for real-time monitoring of students' fatigue states during online classes and could also provide practical strategies for in-person education.