ABSTRACT
Due to the COVID-19 pandemic, the demand for distance learning has significantly increased in higher education institutions. This type of learning is usually supported by Web-based learning systems such as Massive Open Online Courses (Coursera, edX, etc.) and Learning Management Systems (Moodle, Blackboard-Learn, etc.). However, in this remote context, students often lack feedback and support from educational staff, especially when they face difficulties or challenges. For that reason, this work presents a Prediction-Intervention approach that (a) predicts students who present difficulties during an online learning course, based on two main learning indicators, namely engagement and performance rates, and (b) offers immediate support to students, tailored to the problem they are facing. To predict students' issues, our approach considers ten machine learning algorithms of different types (standalone, ensemble, and deep learning) which are compared to determine the best performing ones. It has been experimented with a dataset collected from the Blackboard-Learn platform utilized in an engineering school called ESIEE-IT in France during 2021-2022 academic year, showing thus quite promising results. © 2022 IEEE.
ABSTRACT
Crisis information dissemination plays a key role in the development of emergency responses to epidemic-level public health events. Therefore, clarifying the causes of crisis information dissemination and making accurate predictions to effectively control such situations have attracted extensive attention. Based on media richness theory and persuasion theory, this study constructs an index system of crisis information dissemination impact factors from two aspects: the crisis information publisher and the published crisis information content. A multi-layer perceptron is used to analyze the weight of the index system, and the prediction is transformed into a pattern classification problem to test crisis information dissemination. In this study, COVID-19 is considered a representative event. An experiment is conducted to predict the crisis information dissemination of COVID-19 in two megacities. Data related to COVID-19 from these two megacities are acquired from the well-known Chinese social media platform Weibo. The experimental results show that not only the identity but also the social influence of the information publisher has a significant impact on crisis information dissemination in epidemic-level public health events. Furthermore, the proposed model achieves more than 95% test accuracy, precision rate, recall value and f1-score in the prediction task. The study provides decision-making support for government departments and a guide for correctly disseminating crisis information and public opinion during future epidemic-level public health events.
ABSTRACT
In order to predict the COVID-19 outbreak, several epidemiological models are used around the world to predict the number of infections and mortality. An accurate predictive model is essential to take appropriate action. Based on the Wuhan epidemic data, considering that the virus infection rate in the traditional SEIR model cannot be automatically predicted and the infection situation of patients in the incubation period is not considered, this article first improves the SEIR model to increase the number of confirmed admissions, and secondly based on LSTM and The SEIR model predicts confirmed and potential cases of the epidemic. To a certain extent, it can provide a reference for people to predict the development trend of the epidemic under the current prevention and control measures. © 2022 IEEE.