Online Public Opinion Research Articles

Public Discussions on Climate Crisis in the "New Media of Government": Trends, Dilemmas, and Pathways

In the ever-changing era of all-media development, the new government media has accelerated its development and played an irreplaceable role in promoting the openness of government affairs and guiding online public opinion. However, as a product of the integration of government agencies and new media, new government media has encountered difficulties and challenges in specific communication practices. This paper analyses the dilemmas encountered by new government media in climate crisis communication and proposes solutions regarding role positioning, content improvement, and increasing public participation in climate crisis public issue discussions.

The Role of Online Media in Public Opinion the Small-Town Swot Incident as an Example

Online media is based on the development of network technology and the needs of society and plays an increasingly important role in our lives. Most current studies on online media and public opinion are highly generalized and summarised analyses of social phenomena, with few studies combining the whole case with analysis. The research in this paper adopts a qualitative approach, analyzing the role of social media in various aspects of public opinion through a step-by-step analysis of the development of public opinion and the comments made by the public-on-public opinion in the media. Perhaps it can provide a new research idea for subsequent related studies.

Current Situation and Frontier Evolution of Online Public Opinion on Public Emergencies: Knowledge Graph Analysis Based on Citespace

With the popularity of the Internet and the coverage of new media technologies, the widespread spread of online public opinion on public emergencies has a certain amount of negative impact on public sentiment and social development. In order to systematically grasp the research dynamics and cutting-edge themes of the literature from a macro perspective, this paper took the literature related to online public opinion on public emergencies in CSSCI journals as the research object based on the database of China National Knowledge Infrastructure (CNKI), and comprehensively applied statistical measurement methods to sort out the development lineage, institutional distribution, journal carriers and author influence of this field. Secondly, this study used citespace knowledge mapping technology to visualize and present keywords. Based on this, the clustering outcomes of the LLR algorithm were analyzed to summarize keyword evolution and topic variation from technical, informational, and managerial multipe dimensions, and to contrast the variations in methodologies and topic selection in various literature. Finally, the study identified cutting-edge research directions for the current and future long-term development of the subject, including empirical analysis of big data, information ecological perspectives, and government management.

Manufacturing conflict or advocating peace? A study of social bots agenda building in the Twitter discussion of the Russia-Ukraine war

ABSTRACT After the outbreak of the Russia-Ukraine war, social media become the major contested field for both sides. Social bots are widely involved in the Russia-Ukraine war discussion as communication actors. However, how social bots build the war agenda has not been well answered. This study explores the role of social bots through time series analysis and Structural Topic Model. The study finds that at the aggregate level there is a two-way agenda-setting between social bots and human accounts, and at the secondary level, social bots show different or even opposite agenda-setting effects in national/regional discussion. In addition, we find that social bots exhibit multiple positions in the conversation, reflecting the complexity of the manipulators behind them. This multiplicity of positions reveals that the role played by social bots is still based on the opposition of one side to the other, and the end result may exacerbate the conflict of online public opinion.

Research on two-stage public opinion evolution configuration path based on fuzzy-set qualitative comparative analysis

PurposeUnder 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.Design/methodology/approachTaking 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.FindingsThe 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.Practical implicationsThis research can provide reference for regulators to timely grasp the initiative, discourse power and leadership of public opinion development.Originality/valueResearch 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.

Cyberemotions in the Era of New Media

The introduction of new media has accelerated changes in the generation and delivery of information. Cyberemotions, as a new type of public opinion, can be more contagious and propagate in more diverse ways than traditional public sentiments. The emotions of internet users have a rising influence on the progression of recent significant social events. In order to spark additional discussion on online sentiment modulation and online public opinion tracking, this article presented an overview of cyberemotions definition and key analytical methodologies in existing online sentiment research, as well as a synopsis of major components of cyberemotions.

AHP-based Research on Specific Public Opinion Generation Mechanism and Response Plan

The emergence and development of mobile social networks have led to the rapid generation and evolution of online public opinion in a very short period of time. In order to guide and control the mobile network public opinion scientifically and effectively, the Delphi method is used to analyze the "attractiveness of topics", "user's activity", "user's psychology", "mutual influence among different users" and "platform recommendation algorithm". The quantitative model of the effect of online public opinion dissemination is constructed by using the Delphi method from five dimensions: "attractiveness of topics", "users' activity", "users' psychology", "mutual influence among different users" and "platform recommendation algorithm"; and the weight distribution of each index is analyzed by using the Analytic Hierarchy Process (AHP) through the construction of judgment matrix and relevant calculations. The specific analysis of the distribution of each indicator is carried out by using the Analytic Hierarchy Process (AHP), and the response strategies of Internet public opinion communication are proposed from three levels of government, media platforms and the public for the communication effects in Internet public opinion communication, which have certain practical significance.

Gu Ailing Eileen a Comparative Study on Media Reporting Agenda and Microblog Agenda – Take the Original Report of Xinhua News Agency and the Hot Search Terms on Weibo, for Example

During the 2022 Beijing Winter Olympic Games, the Olympic champion Gu Ailing Eileen became popular and gained a lot of attention in the Chinese and foreign media. With the rise of popularity and influenced by online public opinion, Gu Ailing Eileen's nationality and excellent academic performance have triggered scrambling media reports, which has become a typical case of the dilemma of public crisis communication and public discussion in China. Based on the agenda theory, the paper makes a comparative study on the relevant entries and news content based on Gu Ailing in Sina Weibo and Xinhua News Agency, and tries to explore the differences in the relationship between them from the perspective of the agenda.

Multimodal negative sentiment recognition of online public opinion on public health emergencies based on graph convolutional networks and ensemble learning

To improve the effect of multimodal negative sentiment recognition of online public opinion on public health emergencies, we constructed a novel multimodal fine-grained negative sentiment recognition model based on graph convolutional networks (GCN) and ensemble learning. This model comprises BERT and ViT-based multimodal feature representation, GCN-based feature fusion, multiple classifiers, and ensemble learning-based decision fusion. Firstly, the image-text data about COVID-19 is collected from Sina Weibo, and the text and image features are extracted through BERT and ViT, respectively. Secondly, the image-text fused features are generated through GCN in the constructed microblog graph. Finally, AdaBoost is trained to decide the final sentiments recognized by the best classifiers in image, text, and image-text fused features. The results show that the F1-score of this model is 84.13% in sentiment polarity recognition and 82.06% in fine-grained negative sentiment recognition, improved by 4.13% and 7.55% compared to the optimal recognition effect of image-text feature fusion, respectively.

Research on Influencing Factors of Public Opinion Information Forwarding Behavior of Generation Z Group

[Purpose/Significance] With the continuous development of network technology, the ways of information dissemination become more and more diversified, and the threshold of information dissemination becomes lower and lower. This not only facilitates people's life, but also brings information fog, information polarization and other problems, causing great harm to the network environment. Through the research on the forwarding behavior of Z generation group's public opinion information, this study finds out the influencing factors, so as to help relevant departments improve the network environment and put forward new ideas for the management and control of online public opinion information. [Method/Process] In this study, through questionnaire survey and semi-structured interview, a sample survey was conducted on the "group in Hefei, and the grounded theory was analyzed with the help of Nvivo12 software. A comprehensive research model of influencing factors of public opinion information forwarding behavior of Generation Z group was constructed, and the characteristics of Generation Z group were analyzed. [Result/Conclusion] The research shows that information content mediates the attributes of information receivers. The intermediary role of consumers' internal state in the process of e-commerce anchor attribute influencing consumers' online purchase intention; The external environment plays a regulatory role in the transmission chain of public opinion information.

Review of Artificial Intelligence in Political Science Research – Focusing on Estimation of Online Public Opinion

세계가 인공지능 기술에 집중하고 있다. 미래에 적응하고 리드하기 위해 다양한 산업에서 인공지능 기술을 적용하기 위해 노력하고 있다. IT 기술과 인터넷의 발전은 사람들의 삶을 크게 바꿔 놓았다. 사람들이 온라인 공간에 남기는 매일의 디지털 흔적을 활용하기 위한 노력은 여전히 부족하다. 이는 온라인에 존재하는 엄청난 양의 데이터를 다루기 위해서는 많은 리소스와 기술을 요구하기 때문이다. 본 연구는 여론 측정 방식에 있어 방법의 변화를 설명하고 인공지능과 같은 신기술의 적용으로 인해 발생할 수 있는 문제를 설명한다. 여론은 정치학에서 매우 중요한 주제이다. 연구자들은 서베이를 통해 여론을 측정하였고 인공지능을 활용한 방법을 탐구하기 시작했다. 오피니언 마이닝 방법 중 하나인 감성분석방법을 통해 텍스트에서 감성을 추출할 수 있다. 이전에는 감성사전을 활용해 감성분석을 수행했고 최근에는 BERT와 같이 훈련된 인공지능을 활용한 감성분석 방법을 활용한다. 하지만, 인공지능을 활용함에 있어 여러 어려움이 존재한다. 온라인 상의 텍스트는 일반적인 형태가 아닌 독특한 모습을 띄기 때문에 이를 고려한 학습이 이루어져야 하고 적용 가능한 데이터셋을 만들기 위해서는 큰 비용을 지불해야한다. 현재는 텍스트 데이터만을 활용하지만 온라인 상에는 이미지 및 비디오와 같은 형태의 데이터도 존재한다. 이와 더불어 인공지능 모델에 대한 분석이 어렵다. 모델은 입력한 데이터를 통해 스스로 알고리즘을 학습하고, 이러한 과정을 연구자가 세부적으로 분석할 수 없다. 학습을 수행하기 위해서는 높은 연산능력을 보유한 컴퓨터 장비가 필요하고 이는 일반 연구자에게 큰 장애물로 존재할 수 있다. 하지만 인공지능은 이미 우리에 삶에 크게 들어와 있다. 정치현상에 대한 보다 깊은 이해를 위해 연구자들은 인공지능 기술의 적용을 위해 적극적으로 노력해야 한다.

Research on Efficient Work Innovation Effect Evaluation Based on Real-Time Online Public Opinion Data Classification and Detection Algorithm

Various heterogeneous network resources are collected through web crawlers, and after preprocessing such as data cleaning, they are written into the data center. And implement data mining technologies such as classification, clustering, association rules and anomaly detection. If an enterprise wants to maintain a good development ability and maintain a correct development trend, it must pay attention to and do a good job in ideological and political work, and take ideological and political work as the guiding light of its own operation and development. Improved the stability and accuracy of clustering results. The news topics are clustered to form topics, and the topic tracking technology is used to track specific news topics to achieve personalized services.

Analysis of Network Public Opinion Guidance Strategies of Various Communication Subjects in Natural Crisis Events: Take Chongqing Bush fire Incident as the Example

With the rapid development of media technology, the online public opinion about the Chongqing Bush Fire has continued to ferment with the changing situation of the event and even influenced the development of the event to a certain extent. This paper takes central media, Chongqing local media and we media as the research objects, and compares and analyzes the different strategies and characteristics of every communication subject for the guidance of online public opinion, hoping to provide useful reference for media practitioners in the future guidance of online public opinion, in order to play a positive role of social media in the process of information and social communication.

Impact of reputation on hospitality profitability: impact of service failure online exposure on revenue performance – evidence from the hotel industry in China

Diseño/metodología/enfoqueEste estudio utiliza los datos reales de ingresos por habitación disponible (RevPAR) de 10 hoteles implicados en el incidente y cinco segmentos de mercado diferentes durante 2016-2019. Se utiliza el método de estudio de sucesos (ESM) para investigar el efecto de la exposición en línea en el rendimiento de los ingresos de los hoteles.ObjetivoUtilizando como caso de estudio un vídeo que revela prácticas antihigiénicas en hoteles chinos de cinco estrellas, este estudio pretende comprender el impacto de la exposición online de fallos en el servicio sobre el rendimiento de los ingresos hoteleros en términos de gravedad, magnitud y duración, así como identificar las características y los factores de respuesta del hotel que influyen en la recuperación de los ingresos.ResultadosEste estudio confirma el importante efecto negativo de la exposición online, tardando los hoteles casi nueve meses en recuperarse totalmente. Los resultados indican que el tamaño del hotel, su antigüedad y la estrategia de respuesta desempeñan un papel importante en la reducción del impacto negativo. Además, este estudio revela los efectos indirectos dinámicos de la exposición online en diferentes segmentos del mercado hotelero. Estos efectos cambian de un efecto competitivo a un efecto contagioso con una disminución de las calificaciones de la categoría o clase hotelera.Implicaciones prácticasLos revenue managers de los hoteles de categoría baja deberían tomar medidas eficaces para evitar posibles repercusiones negativas de los fallos en el servicio de otros hoteles. Los directores de hotel podrían considerar la sinergia de diferentes estrategias en lugar de una única estrategia de respuesta para minimizar las pérdidas.Originalidad/valorEste estudio amplía teóricamente los conocimientos sobre el impacto negativo de la exposición online en los ingresos de los hoteles chinos. Además, los resultados examinan los efectos indirectos dinámicos en hoteles de diferentes segmentos. Además, amplían los resultados existentes sobre el impacto negativo de las crisis de opinión pública online.

Multimodal Emotion Recognition and Fluctuation: A Study on Sentiment Analysis of Online Public Opinion

Emotion is an important way for individuals to express their views on the Internet and an important variable that shapes public opinion. Considering the multimodality of data, such as text, picture and video, and the subtlety of emotional expression, a multimodal sentiment analysis model that addresses content involving difference senses, such as sight, hearing and touch at the same time is very necessary. This study outlines the basic steps, classification strategies and research methods of sentimental analysis and acknowledges the differences between sentimental analyses on text, picture and video. As multimodal sentiment recognition is still in its initial stage, there’s still room for improvement in cross-disciplinary research on multimodal data of text, picture, audio, video in terms of weighted scoring, complex emotion and intensity recognition. It’s concluded that future studies should focus on the intensity of different emotions, multimodal data fusion and how weighted scoring influences an emotion recognition model and explore application possibilities.

Exploring the impact of sentiment on multi-dimensional information dissemination using COVID-19 data in China

The outbreak of information epidemic in crisis events, with the channel effect of social media, has brought severe challenges to global public health. Combining information, users and environment, understanding how emotional information spreads on social media plays a vital role in public opinion governance and affective comfort, preventing mass incidents and stabilizing the network order. Therefore, from the perspective of the information ecology and elaboration likelihood model (ELM), this study conducted a comparative analysis based on two large-scale datasets related to COVID-19 to explore the influence mechanism of sentiment on the forwarding volume, spreading depth and network influence of information dissemination. Based on machine learning and social network methods, topics, sentiments, and network variables are extracted from large-scale text data, and the dissemination characteristics and evolution rules of online public opinions in crisis events are further analyzed. The results show that negative sentiment positively affects the volume, depth, and influence compared with positive sentiment. In addition, information characteristics such as richness, authority, and topic influence moderate the relationship between sentiment and information dissemination. Therefore, the research can build a more comprehensive connection between the emotional reaction of network users and information dissemination and analyze the internal characteristics and evolution trend of online public opinion. Then it can help sentiment management and information release strategy when emergencies occur.

Research on Optimization of Public Opinion Supervision Model of Social Network Platform Based on Evolutionary Game

Network environments have recently emerged as a considerable research area. In addition to government supervision, platform supervision is also critical to improve network environments. So, we should improve the social network platform’s single regulatory model. Against this background, we described public opinion supervision as a game between marketing accounts, netizens, and the platform. Unlike previous studies, we considered the influence of marketing accounts on online public opinion. Because of the players’ bounded rationality, we built an evolutionary game model, and by solving it, we obtained the evolutionarily stable strategy (ESS). Then, we analyzed the influence of relevant parameters on the evolutionary stable state. Our research results show that if the authenticity of the information is not high, to not publish is the best choice for the marketing account, and to not participate is the best choice for the netizen. The platform penalty for the marketing account is also directly related to the marketing account’s decision making. The platform penalty for the government, as well as the increase in the penalty risk coefficient, considerably affected the choice of platform. Finally, we put forward the “pre-event–in-the-event–post-event” three-stage supervision model, which provides countermeasures and suggestions for all parties to jointly maintain the network environment.

Crisis Management Experience from Social Media: Public Response to the Safety Crisis of Imported Aquatic Products in China during the Pandemic

China's outbreak related to cold-chain aquatic product quality and safety in 2020 caused public panic and further led to a crisis in China's aquatic industry. This paper uses topic clustering and emotion analysis methods to text-mine the comments of netizens on Sina Weibo to study the main features of the public's views on the administration's crisis management measures and to provide experience for future imported food safety management. The findings show that for the imported food safety incident and the risk of virus infection, the public response had four types of characteristics: a higher proportion of negative emotion; a wider range of information demand; attention paid to the whole imported food industry chain; and a differentiated attitude towards control policies. Based on the online public response, countermeasures to further improve the management ability of imported food safety crises are proposed as follows: the government should pay active attention to the development trend of online public opinion; work more on exploring the content of public concern and emotion; strengthen the risk assessment of imported food and establish the classification and management measures of imported food safety events; construct the imported food safety traceability system; build a special recall mechanism for imported food safety; and improve the cooperation between government and media, enhancing the public's trust in policies.

Risk Management of Negative Online Public Opinion in a Tertiary Hospital Based on the Kaiser Model

Objectives: In this study, we analyzed negative online public opinion in tertiary hospitals and evaluated corresponding risk by applying the Kaiser Model. Methods: Through data and expert group discussion, combined with the hospital's actual negative online public opinion management, we determined the opinions posing higher risk. The hospital's risk questionnaire for negative opinion was designed based on the Kaiser Model. The whole hospital staff was then trained and investigated. An Excel worksheet was used for statistical analysis and risk calculation.Results: According to the ranking of risk value, the top 5 negative online public opinions were drug supply and demand, in-hospital parking, handling of public health emergencies, the service attitude of hospital guidance staff, and interpretation of medical insurance policies. Conclusion: The hospital needs to revise and improve the emergency response plan for negative online public opinion based on the analysis results and reports of opinion risks. This is helpful for strengthening hospital-level emergency training, improving the hospital's ability to manage negative opinion risks, and promoting the hospital to become passive about negative online public opinion.

Innovative Technology Method Based on Evolutionary Game Model of Enterprise Sustainable Development and CNN–GRU

Realizing the sustainable innovation growth of enterprises is one of the important research directions of management science. Traditional enterprise growth innovation methods cannot effectively estimate the emotional tendency of online public opinion (PO), and they cannot guide the effective growth of enterprises. For this reason, This paper proposes an enterprise growth innovation technology based on the evolutionary game (EG) model of sustainable development and deep learning (DL). Firstly, by obtaining the game payment matrix between network users and enterprises, combined with the deep neural network model, the PO evolution model of the enterprise growth network was constructed and solved. Then, a convolutional neural network (CNN) model was used to extract sequence features from global information, and a gated recurrent unit (GRU) was used to consider the context. A DL network model based on CNN–GRU was proposed. Finally, by introducing the EG model, a stable strategy was generated through the dynamic adjustment of the whole system, which improved the accuracy of online PO judgment. Through simulation experiments, the enterprise growth innovation method proposed in this paper was compared with the other three methods. The results show that the accuracy, precision, recall, and f1 value of this method are 92.21%, 89.33%, 91.86%, and 91.64%, respectively, which are better than the other three methods. This method is of great significance for promoting enterprise innovation technology and sustainable development of enterprises.