To Mask or Not To Mask? A Machine Learning Approach to Covid News Coverage Attitude Prediction Based on Time Series and Text Content

In the past few decades, with the explosion of information, a large number of computer scientists have devoted themselves to analyzing collected data and applying these findings to many disciplines. Natural language processing (NLP) has been one of the most popular areas for data analysis and pattern recognition. A significantly large amount of data is obtained in text format due to the ease of access nowadays. Most modern techniques focus on exploring large sets of textual data to build forecasting models;they tend to ignore the importance of temporal information which is often the main ingredient to determine the performance of analysis, especially in the public policy view. The contribution of this paper is two-fold. First, a dataset called COVID-News is collected from three news agencies, which consists of article segments related to wearing masks during the COVID-19 pandemic. Second, we propose a long-short term memory (LSTM)-based learning model to predict the attitude of the articles from the three news agencies towards wearing a mask with both temporal and textural information. Experimental results on COVID-News dataset show the effectiveness of the proposed LSTM-based algorithm. © 2022 IEEE.

Public Opinion Analysis and Popularity Prediction for COVID-19 Hot Search Based on Weibo

Since the end of 2019, a new type of coronavirus pneumonia (COVID-19) has broken out in Wuhan, and various topics about the development of the epidemic have spread in full swing on the Sina Weibo. In this paper, the web crawler is used to capture the relevant Weibo and popularity of the hot searches during the COVID-19 outbreak, and the Weibo related to the epidemic are extracted by the Bayesian text classification method. Then, the potential Dirichlet model (LDA) was established to obtain the public opinion topic model, and ten public opinion topics were obtained to analyze the public opinion changes with the development of the epidemic. According to the topic model and the influence of daily time point on the popularity of Weibo, a multiple linear regression model is established to predict the popularity. Real-time analysis of changes in public opinion concerns provides reference for decision-making on epidemic prevention and control and information release. © 2022 IEEE.