Search results

This study aims to enhance the classification and processing of online appeals by employing a deep-learning-based method. This method is designed to meet the requirements for precise information categorization and decision support across various management departments.

This study leverages the ALBERT–TextCNN algorithm to determine the appropriate department for managing online appeals. ALBERT is selected for its advanced dynamic word representation capabilities, rooted in a multi-layer bidirectional transformer architecture and enriched text vector representation. TextCNN is integrated to facilitate the development of multi-label classification models.

Comparative experiments demonstrate the effectiveness of the proposed approach and its significant superiority over traditional classification methods in terms of accuracy.

The original contribution of this study lies in its utilization of the ALBERT–TextCNN algorithm for the classification of online appeals, resulting in a substantial improvement in accuracy. This research offers valuable insights for management departments, enabling enhanced understanding of public appeals and fostering more scientifically grounded and effective decision-making processes.

Under the background of coexistence of information overload and information fragmentation, it is of great significance to identify influencing factors and reveal the evolution logic of public opinion for public opinion governance.

Taking 24 hot social events as research cases, firstly, the evolution process of public opinion was divided into initial stage and response stage. Secondly, eight antecedent variables were extracted for qualitative comparative analysis of fuzzy sets. Finally, the configuration path of public opinion evolution results was summarized.

The research showed that compared with the initial stage, the influencing factors in the reaction stage played a key role in the continuous evolution of public opinion. The influencing factors in the initial stage and response stage played an indispensable role in promoting the evolution of public opinion to calm down.

This research can provide reference for regulators to timely grasp the initiative, discourse power and leadership of public opinion development.

Research on the two-stage configuration path of public opinion evolution is helpful to clarify the key factors affecting the evolution trend of online public opinion of hot events.

The 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.

Based 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.

Research 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.

The 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.

This paper aims to investigate the impacts of rumors' information characteristics on people's believing and spreading of rumors online.

This study employed a mixed-methods approach by combining qualitative and quantitative methods. In study 1, the authors explored different types of rumors and their information source characteristics through qualitative research. In study 2, the authors utilized the findings from study 1 to develop an empirical model to verify the impact of these characteristics on the public's behaviors of believing and spreading rumors by content analysis and quantitative research.

The results show that five information source characteristics – credibility, professionalism, attractiveness, mystery and concreteness – influence the spreading effect of different types of rumors.

This study contributes to rumor spreading research by deepening the theory of information source characteristics and adding to the emerging literature on the COVID-19 pandemic.

Insights from this research offer important practical implications for policymakers and online-platform operators by highlighting how to suppress the spread of rumors, particularly those associated with COVID-19.

This research introduces the theory of information source characteristics into the field of rumor spreading and adopts a mixed-methods approach, taking COVID-19 rumors as a typical case, which provides a unique perspective for a deeper understanding of rumor spreading's antecedences.