The outbreak of Corona Virus Disease 2019 (COVID-19) in various countries at the end of last year has transferred traditional face-to-face teaching to online education platforms, which directly affects the quality of education. Taking user satisfaction on online education platforms in China as the research object, this paper uses a questionnaire survey and web crawler to collect experience data of online and offline users, constructs a customer satisfaction index system by analyzing emotion and the existing literature for quantitative analysis, and builds aback propagation (BP) neural network model to forecast user satisfaction. The conclusion shows that users’ personal factors have no direct influence on user satisfaction, while platform availability has the greatest influence on user satisfaction. Finally, suggestions on improving the online education platform are given to escalate the level of online education during the COVID-19 pandemic, so as to promote the reform of information-based education.

The wide dissemination of false information and the frequent occurrence of extreme speeches on online social platforms have become increasingly prominent, which impact on the harmony and stability of society. In order to solve the problems in the dissemination and polarization of public opinion over online social platforms, it is necessary to conduct in-depth research on the formation mechanism of the dissemination and polarization of public opinion. This article appends individual communicating willingness and forgetting effects to the Susceptible-Exposed-Infected-Recovered (SEIR) model to describe individual state transitions; secondly, it introduces three heterogeneous factors describing the characteristics of individual differences in the Jager-Amblard (J-A) model, namely: Individual conformity, individual conservative degree, and inter-individual relationship strength in order to reflect the different roles of individual heterogeneity in the opinions interaction; thirdly, it integrates the improved SEIR model and J-A model to construct the SEIR-JA model to study the formation mechanism of public opinion dissemination and polarization. Transmission parameters and polarization parameters are simulated and analyzed. Finally, a public opinion event from the pricing of China’s self-developed COVID-19 vaccine are used, and related Weibo comment data about this event are also collected so as to verify the rationality and effectiveness of the proposed model.

With the rapid development of “We media” technology, netizens can freely express their opinions regarding enterprise products on a network platform. Consequently, online public opinion about enterprises has become a prominent issue. Negative comments posted by some netizens may trigger negative public opinion, which can have a significant impact on an enterprise’s image. From the perspective of helping enterprises deal with negative public opinion, this paper combines user portrait technology and a random forest algorithm to help enterprises identify high-risk users who have posted negative comments and thus may trigger negative public opinion. In this way, enterprises can monitor the public opinion of high-risk users to prevent negative public opinion events. Firstly, we crawled the information of users participating in discussions of product experience, and we constructed a portrait of enterprise public opinion users. Then, the characteristics of the portraits were quantified into indicators such as the user’s activity, the user’s influence, and the user’s emotional tendency, and the indicators were sorted. According to the order of the indicators, the users were divided into high-risk, moderate-risk, and low-risk categories. Next, a supervised high-risk user identification model for this classification was established, based on a random forest algorithm. In turn, the trained random forest identifier can be used to predict whether the authors of newly published public opinion information are high-risk users. Finally, a back propagation neural network algorithm was used to identify users and compared with the results of model recognition in this paper. The results showed that the average recognition accuracy of the back propagation neural network is only 72.33%, while the average recognition accuracy of the model constructed in this paper is as high as 98.49%, which verifies the feasibility and accuracy of the proposed random forest recognition method.

At present, rumors appear frequently in social platforms. The rumor diffusion will cause a great impact on the network order and the stability of the society. So it's necessary to study the diffusion process and develop the rumor control strategies. This article integrates three heterogeneous factors into the SEIR model and designs an individual state transition mode at first. Secondly, based on the influencing factors such as the trust degree among individuals, an individual information interaction mode is constructed. Finally, an improved SEIR model named SEIR-OM model is established, and the diffusion process of rumors are simulated and analyzed. The results show that: (1) when the average value of the interest correlation is greater, the information content deviation is lower, but the rumor diffusion range will be wider. (2) The increase of the average network degree intensifies influence of rumors, but its impact on the diffusion has a peak. (3) Adopting strategies in advance can effectively reduce the influence of rumors. In addition, the government should enforce rumor-refuting strategies right after the event. Also, the number of rumor-refuting individuals must be paid attention to. Finally, the article verifies the rationality and effectiveness of the SEIR-OM model through the real case.

As an important part of human resources, college graduates are the most vigorous, energetic, and creative group in society. The employment of college graduates is not only related to the vital interests of graduates themselves and the general public, but also related to the sustainable and healthy development of higher education and the country’s prosperity through science and education. However, the outbreak of COVID-19 at the end of 2019 has left China’s domestic labor and employment market in severe condition, which has a significant impact on the employment of college graduates. Based on the situation, the Chinese government has formulated a series of employment promotion policies for college graduates in accordance with local conditions to solve the current difficulties in employment of college graduates during the COVID-19Pandemic. Do these policies meet the expectations of the people? Is the policy implementation process reasonable? All these issues need to be tested and clarified urgently. This paper takes the employment promotion policy of college graduates under the COVID-19 as the research object, uses the PMC index model to screen the policy texts, obtains two perfect policy texts, and uses the Weibo comments to construct the evaluation model of policy measures support degree to analyze the social effects of employment promotion policies for college graduates. The results show that the public’s support degree with the employment promotion policies for college graduates under COVID-19 needs to be improved. Among them, the public has a neutral attitude towards position measures and transference measures but is obviously dissatisfied with subsidy measures and channel measures. Finally, suggestions for improving policy are given to make the employment policy in line with public opinion and effectively relieve the job hunting pressure of college graduates.