网络舆情传播主体分类与挖掘方法研究

Evolution mechanism and influencing factors of multidimensional public opinion dissemination from the perspective of game theory

The DR-SCIR network public opinion propagation model was employed to study the characters of S-state users stopping transmitting information for the first time and secondary transmission of immune users. The model takes into account symmetry and complexity such as direct immunization and social reinforcement effect, proposes the probability of direct immunity Psr and the probability of transform from the immune state to the hesitant state Prc, and divides public opinion information into positive public opinion and negative public opinion based on whether the public opinion information is confirmed. Simulation results show that, when direct immunity Psr = 0.5, the density of I-state nodes in the model decreased by 54.12% at the peak index; when the positive social reinforcement effect factor b = 10, the density of I-state nodes in the model increased by 16.67% at the peak index; and when the negative social reinforcement effect factor b = -10, the density of I-state nodes in the model decreased by 55.36% at the peak index. It shows that increasing the positive social reinforcement effect factor b can promote the spread of positive public opinion, reducing the negative social reinforcement effect factor b can control the spread of negative public opinion, and direct immunization can effectively suppress the spread of public opinion. This model can help us better analyze the rules of public opinion on social networks, so as to maintain a healthy and harmonious network and social environment.

Earthquakes endanger lives and properties and trigger widespread online public opinion. If the government fails to implement emergency measures quickly, the risks associated with this online public opinion may escalate and present significant challenges in managing it. To solve this issue, this paper investigates the M5.7 earthquake in Yibin, China, as a case study, drawing data from China’s Sina Weibo. It also develops an evolutionary model of earthquake online public opinion using the life cycle theory of public opinion dissemination, public opinion crisis management theory, and system dynamics methods. This study chooses a system dynamic model because it can capture overall trends and feedback cycles. This approach provides a comprehensive view of the evolution of the whole system’s behavior and public opinion during the crisis. This model analyzes the evolution of the online public opinion of the earthquake from the perspective of the earthquake, netizens (social media users), media, and government. This study explores the differences between online public opinion by adjusting the size of different variables in the model. This provides an entry point for better control of the development and communication of earthquake online public opinion. The findings indicate that, following the earthquake, the media exerted the most significant influence on public opinion, mainly through media participation, diffusion, and impact, demonstrating a significantly positive correlation with the magnitude of public opinion. Moreover, the simulation revealed that the government is leading in preventing and controlling online public opinion. This study presents the following innovations: (1) It builds a comprehensive online public opinion model for earthquakes, which provides insights for studying online public opinion regarding other sudden natural disasters. (2) It employs system dynamics to simulate earthquake online public opinion, providing countermeasures and recommendations for the government to manage and regulate this discourse effectively.

PurposeThe sudden outbreak of COVID-19 has become a major public health emergency of global concern. Studying the Internet public opinion dissemination mechanism of public health emergencies is of great significance for creating a legalized network environment, and it is also helpful for managers to make scientific decisions when encountering Internet public opinion crisis.Design/methodology/approachBased on the analysis of the process of spreading the Internet public opinion in major epidemics, a dynamic model of the Internet public opinion spread system was constructed to study the interactive relationship among the public opinion events, network media, netizens and government and the spread of epidemic public opinion. The Shuanghuanglian event in COVID-19 in China was taken as a typical example to make simulation analysis.FindingsResearch results show three points: (1) the government credibility plays a decisive role in the spread of Internet public opinion; (2) it is the best time to intervene when Internet public opinion occurred at first time; (3) the management and control of social media are the key to public opinion governance. Besides, specific countermeasures are proposed to assist control of Internet public opinion dissemination.Originality/valueThe epidemic Internet public opinion risk evolution system is a complex nonlinear social system. The system dynamics model is used to carry out research to facilitate the analysis of the Internet public opinion propagation mechanism and explore the interrelationship of various factors.

Background Food safety scandals pose severe threats to public health and social stability, often triggering widespread emotional reactions and disruptive public opinion crises. Understanding the mechanisms driving public opinion evolution in such scenarios is crucial for effective crisis management. Method To investigate these mechanisms, we developed the HK-SNPR model, which incorporates differentiated dissemination propensities. The model was applied to analyze public opinion data from the "McDonald's relabeling expired food" incident in China. Result The analysis revealed that negative opinions from high-influence users are most likely to provoke large-scale dissemination of public sentiment. Authoritative individuals exerted stronger influence than professional experts. Furthermore, the interaction between incident severity and individual involvement significantly steered the evolution of public opinion. Additionally, positive opinions played a critical yet asymmetric role, serving as a key leverage point for accelerating the attenuation of public opinion crises. Conclusion These findings provide important insights for the effective management and control of public opinion related to food safety scandals, highlighting the pivotal influence of key user groups and the stabilizing potential of positive information.

PurposeThe outbreak and continuation of COVID-19 have spawned the transformation of traditional teaching models to a certain extent. The Chinese Ministry of Education’s guidance on “keep learning and teaching during class suspension” has made OTC and learning (OTC) become routinized, and the public’s emotional attitudes toward OTC have also evolved over time. The purpose of this study is to segment the emotional text data and introduce it into the topic model to reveal the evolution process and stage characteristics of public emotional polarity and public opinion of OTC topics during public health emergencies in the context of social media participation. The research has important guiding significance for the development of OTC and can influence and improve the efficiency and effect of OTC to a certain extent. The analysis of online public opinion can provide suggestions for the government and media to guide the trend of public opinion and optimize the OTC model.Design/methodology/approachThis paper takes the topic of “OTC” on Zhihu during the COVID-19 epidemic as an example, combined with the characteristics of public opinion changes, chooses Boson emotional dictionary and time series analysis method to build an OTC network public opinion theme evolution analysis framework that integrates emotional analysis and topic mining. Finally, an empirical analysis of the dynamic evolution of the communication network for each stage of the life cycle of a specific topic is realized.FindingsThis paper draws the following conclusions: (1) Through the emotional value table and the change trend chart of the number of comments, the analysis found that the number of positive comments is greater than the number of negative comments, which can be inferred that the public gradually accepts “OTC” and presents a positive emotional state. (2) By observing the changing trend of the average daily emotional value of the public, it is found that the overall emotional value shows a stable development trend after a large fluctuation. From the actual emotional value and the fitted emotional value curve, it can be seen that the overall curve fit is good, so ARIMA (12, 1, 6) can accurately predict the dynamic trend of the daily average emotional value in this paper. Therefore, based on the above-mentioned public opinion, emotional analysis research, relevant countermeasures and suggestions are put forward, which is conducive to guiding the development direction of public opinion in a positive way.Originality/valueTaking the topic of “OTC” in Zhihu as an example, this paper combines Boson emotional dictionary and time series to conduct a series of research analyses. Boson emotional dictionary can analyze the public’s emotional tendency, and time series can well analyze the intrinsic structure and complex features of the data to predict the future values. The combination of the two research methods allows for an adequate and unique study of public emotional polarization and the evolution of public opinion.

Current public-opinion propagation research usually focused on closed network topologies without considering the fluctuation of the number of network users or the impact of social factors on propagation. Thus, it remains difficult to accurately describe the public-opinion propagation rules of social networks. In order to study the rules of public opinion spread on dynamic social networks, by analyzing the activity of social-network users and the regulatory role of relevant departments in the spread of public opinion, concepts of additional user and offline rates are introduced, and the direct immune-susceptible, contacted, infected, and refractory (DI-SCIR) public-opinion propagation model based on real-time online users is established. The interventional force of relevant departments, credibility of real information, and time of intervention are considered, and a public-opinion propagation control strategy based on direct immunity is proposed. The equilibrium point and the basic reproduction number of the model are theoretically analyzed to obtain boundary conditions for public-opinion propagation. Simulation results show that the new model can accurately reflect the propagation rules of public opinion. When the basic reproduction number is less than 1, public opinion will eventually disappear in the network. Social factors can significantly influence the time and scope of public opinion spread on social networks. By controlling social factors, relevant departments can analyze the rules of public opinion spread on social networks to suppress the propagate of negative public opinion and provide a powerful tool to ensure security and stability of society.

With the rapid development of short video platforms, they are gradually changing the way information is disseminated and public opinion is guided. To explore the role of short videos in guiding public opinion, this study mainly analyzes data from third-party data platforms and short video media accounts to reveal the mechanism of short videos on the evolution of public opinion. A detailed statistical analysis of the content of relevant videos on the short video platform was conducted, including the number of video views, the number of comments, and their changing trends; An in-depth analysis was conducted on the videos and comments released by self-media and mainstream media. Through content analysis, the study evaluated the communication characteristics of these media in guiding public opinion, including the selective dissemination of information, emotional tendencies, and the shaping of public cognition. The research results show that short video platforms play a significant role in guiding public opinion, and their dissemination characteristics and content selection have a profound impact on the formation and development of public opinion. In particular, self-media and mainstream media play a key role in guiding public opinion. They play a leading role in shaping public opinion through different communication strategies and content presentation.

In recent years, social networks of various type emerge continuously, on which the public opinion spread attracted wider interest. For the public opinion spread, game theory is utilized to model it from the rational game and non-rational game aspects. Later the game analysis is integrated into the network state conversion (NSC) model to experiment on more real situation. Through large amount of simulation experiments, we conclude that, in contrast with rational game, non-rational game can control the spreading speed and the scope of public opinion dissemination and have lower computation complexity. The game analysis can successfully transplant into NSC model, which maintains its inherent nature unchanged.

A multi-particle model applicable to social issues—time-evolution of Japanese public opinion on nuclear energy

This paper studied the public opinion dissemination mechanism of public health events such as avian influenza on WeChat. We collected 25,572 posts related to “avian influenza” and “H7N9” from WeChat accounts and proposed the NRT model to simulate the spread of avian influenza public opinion in WeChat. Fitting results show that it can well explain the information dissemination process and mechanism within the WeChat public account. Then the influence of model parameters on the propagation of network public opinion is further studied. Our research can provide a theoretical basis for network public opinion prediction and prevention, and has great significance for the stability of the network environment.

Research on agricultural monitoring system based on convolutional neural network

To clarify the evolutionary law of major epidemics online public opinion is a prerequisite for targeted public opinion management. This article takes the Novel Coronavirus Pneumonias as an example and proposes a method to predict the hot spots of public opinion in epidemic. We firstly used the python web crawler technology to capture 58916 online public opinion data on the Novel Coronavirus Pneumonias of the Forum on ‘Making the Country Prosperous’ of People’s Daily Online from January to March 2020, and then used the jieba thesaurus for word segmentation and keyword extraction, and performed word frequency statistics to show the hot content of the new crown epidemic network public opinion, then through the keyword association rule mining to find out the hot topics, finally through the information entropy to evaluate the hot topics, and discover potential hot topics in the future.

Individuals are not electrons. But in some situations, they behave very much alike. When it comes to many social and political questions, individuals’ complex attitudes and beliefs must be boiled down to a simple yea (“spin up”) or nay (“spin down”). Although human societies, like physical materials, are very complex, some of their properties can be determined by understanding the interactions that occur between individuals (“atoms”). In particular, the spread of a particular political opinion throughout a society can be modeled as the macroscopic manifestation of the myriad exchanges occurring at the local level between individuals and their neighbors. This model can be used to gain a qualitative foothold on the evolution of public opinion in Iraq for or against the U.S.-led occupation. It can also provide a mathematical instantiation of the “oil-spot” strategy proposed by Krepinevich (2005), which in turn could lead to a practical tool for commanders needing to allocate public relations resources in Iraq.

Researches on opinion dynamics aim at modeling the formation and evolution of public opinions from individual level. This paper reviews basic models and results in the field of opinion dynamics, focusing on the starting points and the modeling principles. The influence of network structure on the dynamical result is discussed. The comparison of models and results with empirical data on the Internet is emphasized. By employing the particularities of the Internet, we propose several future research issues in the area.