Online Public Opinion Research Articles

Public Opinion Management of Public Crisis Events in the New Media Era — Taking 3.21 China Eastern Airlines Flight Accident as an Example

In the era of new media, press conferences and TV news are no longer the only channels for information exchange. Communication software, major public accounts, online forums and other ways have become the channel of the masses to have their voices to be heard. After the occurrence of public crisis, public opinion based management becomes a link that the government is required to attach importance to. Positive public opinion management can greatly reduce the negative impact of public crisis events. Therefore, the authority, accuracy and timeliness of information disclosure become the key factors. The government, the media and the masses should form a multi-management subject, which can be led by government with multi-party mode to control the trend of public opinion. In addition, the government should uphold the people-oriented concept, and do a good job in psychological counseling for the victims' families, witnesses, rescue workers and other groups to prevent intensified public opinion. In the new media era, the government should be candid and relative, take the initiative, give positive guidance and interact well, so as to form a good ecological environment for online public opinion, improve the handling efficiency of public crisis events, and thus promoting social solidarity and enhancing the ability of the government to handle some issues.

Analysis of Network Public Opinion in New Media Based on BP Neural Network Algorithm

With the rapid development of Internet technology, new media is more and more favored by people and has become an important medium to control online public opinion. Social public opinion caused by new media is also more and more concerned by all walks of life. New media has the characteristics of fast information dissemination, wide dissemination range, and strong arbitrariness of news release. Positive online public voice or negative online public voice will have a very different impact on people’s lives. Some negative online public voice may even constitute a social crisis and seriously affect social public security. In order to analyze and predict the development trend of new media network public opinion, this paper presents a design of improved BP neural network model based on genetic algorithm, which is used to analyze public opinion in new media network. Experimental results show that this way has stronger processing ability and higher warning accuracy for online public opinion event index data. It can provide certain theoretical basis and data support for relevant departments to effectively prevent and manage new media network public opinion events.

A Novel Public Opinion Polarization Model Based on BA Network

At present, the polarization of online public opinion is becoming more frequent, and individuals actively participate in attitude interactions more and more frequently. Thus, online views have become the dominant force in current public opinion. However, the rapid fermentation of polarized public opinion makes it very easy for actual topic views to go to extremes. Significantly, negative information seriously affects the healthy development of the social opinion ecology. Therefore, it is beneficial to maintain national credibility, social peace, and stability by exploring the communication structure of online public opinions, analyzing the logical model of extreme public attitudes, and guiding the communication of public opinions in a timely and reasonable manner. Starting from the J–A model and BA network, this paper explores the specific attributes of individuals and opinion network nodes. By incorporating parameters such as individual conformity and the strength of individual online relationships, we established a model of online group attitude polarization, then conducted simulation experiments on the phenomenon of online opinion polarization. Through simulations, we found that individual conformity and the difference in environmental attitude greatly influence the direction of opinion polarization events. In addition, crowd mentality makes individuals spontaneously choose the side of a particular, extreme view, which makes it easier for polarization to form and reach its peak.

Multidimensional Dynamics and Forecast Models of Network Public Opinions Based on the Fusion of Smart Transportation and Big Data

With the increase of the world’s population, the means of transportation and vehicles that adapt to the times are still difficult to cope with the increase in traffic volume. The traffic problem can be said to be a worldwide problem. However, with the development of artificial intelligence, the emergence of smart transportation has brought new development to modern transportation, and the application of smart transportation and big data is inseparable. In contemporary society, the widespread use of the Internet allows the public to fully exercise their rights to participate in social management and conduct public opinion supervision, which provides a great impetus for the development of online public opinion. However, due to the huge scale of information, some false and harmful information and opinions will inevitably be mixed into it, which will make the network public opinion unable to perform its due function smoothly. Therefore, it is necessary to carry out highly effective management activities on the network public opinion. This paper studies the multidimensional dynamics and prediction model of network public opinion based on the integration of smart transportation and big data; the aim is to design a simple and effective forecasting model to provide traffic management departments with good public opinion forecasting and analysis methods so as to make better decisions. This paper analyzes the related technologies of smart transportation and network public opinion and designs a prediction model of smart transportation network public opinion. Finally, this paper uses rough set theory to optimize the model and compares the data before and after optimization. The results are as follows: the data correlation coefficient before and after optimization is 0.988, and the two-tailed significance level is 0.471, which proves that the results before and after processing are highly correlated, and the two sets of data have no significant difference, proving that the optimization of the model is effective, simplifies the analysis process, and does not change the results.

Measuring Online Public Opinion for Decision Making: Application of Deep Learning on Political Context

Thoughts travel faster and farther through cyberspace where people interact with one another regardless of limitations in language, space, and time. Is a poll sufficient to measure people’s opinions in this era of hyperconnectivity? This study introduces a deep learning method to measure online public opinion. By analyzing Korean texts from Twitter, this study generates time-series data on online sentiment toward the South Korean president, comparing it to traditional presidential approval to demonstrate the independence of the masses’ online discourse. The study tests different algorithms and deploys the model with high accuracy and advancement. The analysis suggests that online public opinion represents a unique population as opposed to offline surveys. The study model examines Korean texts generated by online users and automatically predicts their sentiments, which translate into group attitudes by aggregation. The research method can extend to other studies, including those on environmental and cultural issues, which have greater online presence. This provides opportunities to examine the influences of social phenomenon, benefiting individuals seeking to understand people in an online context. Moreover, it helps scholars in analyzing those public opinions—online or offline—that are more important in their decision making to assess the practicality of the methods.

Online Shopping Brand Sales Based on IoT Big Data Processing.

As a pair of closely related technical fields, “Internet of Things” and “big data” are gradually applied to the analysis of online shopping, which is very beneficial to promote the healthy and orderly development of the online shopping industry. This article uses the big data processing technology of the Internet of Things to analyze the influencing factors of online shopping brand sales based on the data collected by online questionnaires. It draws certain rules from it, and provides relevant marketing strategies for online shopping brand sales to assist its market positioning. According to the survey, the five aspects of online evaluation, brand awareness, online shopping community, online public opinion influence of related brands, and other brand information acquisition channels all have an impact on online brand sales. Especially women aged 25–35 will pay attention to online information, and 195 people will not choose to buy from brands with negative news. And during the purchase process, 186 people will check the online reviews of related brand products. Among them, there are 183 men aged 25–35 who will pay attention to online reviews.

Textual Information Classification of Campus Network Public Opinion Based on BILSTM and ARIMA

To address the problem that it is difficult for traditional opinion analysis models to accurately analyze textual information of campus online public opinion in various formats, a deep learning-based online opinion analysis method is proposed by combining BILSTM and ARIMA models. By using BILSTM sentiment classification model to predict and analyze the text data of campus online public opinion, the sentiment polarity of online public opinion information was well predicted, and the trend prediction of online public opinion was completed by combining ARIMA model difference and temporal preprocessing BILSTM with accuracy values as the original sequence. The simulation results show that the proposed method can better achieve the sentiment prediction of campus online opinion event texts and can predict the general trend of campus online opinion development. The prediction results can well reflect the actual online public opinion and have better prediction accuracy compared with CNN or LSTM models, which can reach more than 80%.

Research on the path choice behavior of donated materials under major epidemics

PurposeIn the face of major disasters, the Chinese people's willingness to donate has increased and the result is that the donation paths have increased. However, there are certain differences in the choice of donation paths for different types of individuals. It is crucial to pay more attention to the attitude and donation path selection of donors and propose strategies to promote individual donation behavior. The purpose of this study is to propose a conceptualized moderated mediation model for testing the linkage between individual attitude and donation path selection through the mediating effect of donors' behavioral intention and the moderating effect of behavioral difficulty perception or social pressure between donors' attitude and their donation path selection.Design/methodology/approachBased on a questionnaire survey of 628 community workers during COVID-19 in China. Self-reported measures were used to obtain data on IA, BI, SP, BDP and DPS. Survey data were used to test the proposed model using hierarchical regression analysis. Mediation analyses with bootstrap via PROCESS were used to ascertain the proposed relationship.FindingsThe results showed that individual attitude are positively related to donation path selection. Moreover, this study finds that behavioral intention serves as a mediator in the relationships between individual attitude and donation path selection. The social pressure and behavioral difficulty perception negatively moderate the relationship between individual attitude and behavioral intention.Research limitations/implicationsThere are still some shortcomings in this study: First, although the data collected at multiple points in this study are all individual data. Future research can add evaluations of relatives, friends or colleagues to individual scheduling of survey subjects to reduce homology errors. Second, although this study has verified the mediating role of the opposite sex, some of the mediating results show that there may be other variables that play a role in the relationship between individual attitudes and donation path selection. In the research on path selection, the integrated theoretical perspective has rich connotations but has not attracted enough attention from the academic community. This research is only based on this single theoretical perspective to construct, verify and explain the model, and there should be other integrated theories. The fit point can be used to analyze the influence mechanism of individual attitudes on the choice of donation path.Practical implicationsFirst of all, we must deepen our understanding of the connotation and role of individuals' attitudes. In the event of a major epidemic, the following two types of measures will be taken to improve individuals' attitudes toward specific donation paths: First, the sponsors of each donation should do their best to donors and provide more information about donations, because the more information resources they have, the stronger the experience of the corresponding donation path, and the more they will choose the path. The sponsor of the second donation must show concern for major epidemics that are prone to occur and a desire to help people affected by disasters, so as to enhance the emotional identity of the donor, thereby increasing the probability of the donor choosing a specific donation path. Secondly, donation sponsors should be wary of the negative influence of social pressure on the donation path selection of individual donors. Donation sponsors can train individuals who are willing to donate, guide them in social relations, online public opinion and other pressure methods and improve the possibility of individuals choosing specific donation routes.Social implicationsDeepen the understanding of the content and effectiveness of the behavioral difficulty perception that has a profound impact on the donor. The greater the tendency to make a path choice is often affected by the individual's perception of the difficulty of behavior. The perception of difficulty of a certain donation path will cause the individual to retreat and inhibit the possibility of the individual choosing the path. Therefore, donation sponsors should take all measures to make their own donation channels simpler and more efficient, thereby reducing the individual's perception of the difficulty of donation behavior.Originality/valueDrawing on TPB theory, a theoretical framework is constructed that specifies the process through which individual attitude affects donation path selection to expand collective understandings of individual attitude in the donation context. Furthermore, the boundary conditions of the underlying process are investigated, which further enhances the contribution of this paper to the extant literature on individual attitude.

Social Public Opinion Communication and Network Legal Management Based on Artificial Intelligence Cognitive Wireless Network

Public opinion supervision is an important part of the national security supervision system. In the Internet era, especially with the rapid development of mobile social media, the position of online public opinion supervision in public opinion supervision is becoming more and more prominent. Internet public opinion supervision has a wide range of subjects, diverse objects, multiple channels, instant and efficient communication speed, and two-way interaction and has its distinctive features, but at the same time there are phenomena such as online rumors, invasion of others' privacy, and venting private anger. The existence of these problems requires strengthening the legal system of public opinion supervision, enhancing the network literacy of Internet users, government management departments, website operators, and other subjects of online public opinion supervision, continuously improving the technical level of online public opinion monitoring, and public opinion guidance ability of network supervision departments, and strengthening the regulation of online public opinion supervision through the improvement and improvement of legal system and coordinated promotion of cyberspace governance. Meanwhile, mobile Internet is the soil for social opinion dissemination. With the development of technology, cognitive wireless network is becoming an important infrastructure in the mobile Internet. Therefore, this paper studies social opinion dissemination and cyber law management in cognitive wireless networks and proposes a cognitive engine model based on artificial intelligence algorithms for cognitive wireless networks for enhancing opinion dissemination and law management. The extended experiments demonstrate the advanced performance and effectiveness of the proposed method in this paper and provide a new technical approach for enhancing public opinion dissemination and legal management.

Characterizing Chinese online public opinions towards the COVID-19 recovery policy

PurposeThe online users’ characteristic information can provide decision support for policy-designing and construction of public strategies. Hence, this paper aims to conduct online public opinion mining on the recovery policy stimulating the economies stroked by COVID-19 epidemic. Also, sentimental analysis is performed to uncover the posters’ emotion towards the target policy.Design/methodology/approachThis paper adopts bidirectional encoder representations from transformers (BERT) as classifier in classification tasks, including misinformation detection, subject analysis and sentimental analysis. Meanwhile, latent Dirichlet allocation method and sentiment formulations are implemented in topic modelling and sentiment analysis.FindingsThe experimental results indicate that public opinion is mainly non-negative to the target policy. The positive emotions mainly focus on the benefits that the recovery policy might bring to stimulate economy. On the other hand, some negative opinions concerned about the shortcomings and inconvenience of the target policy.Originality/valueThe authors figured out the key factors focused by the public opinion on the target recovery policy. Also, the authors indicated pros and cons of the recovery policy by analysing the emotion and the corresponding topics of the public opinion on social media. The findings of the paper can be generalized in other countries theoretically to help them design recovery policy against COVID-19.

Research on the Influencing Factors and Driving Paths of Public Opinions Reversed by Public Emergencies: Clear Set Qualitative Comparative Analysis Based on 30 Cases from 2014 to 2020 (QCA)

Studying the influencing factors and identifying the driving path of public opinion reversal have important practical significance for effectively avoiding the risk of public opinion reversal. Combined with the theory of actor network, the analysis shows that 7 important factors in the public opinion reversal are the antecedent conditions of public opinion reversal in public emergencies. Qualitative comparative analysis identifies the internal motivation and driving path of the reversal of online public opinion. Four core driving paths are obtained. Through the analysis of different condition combination paths, the conclusion is reached: the role of opinion leaders in reversing public opinion in public emergencies is limited; the central government must pay attention to the core role of the response; be wary of graphics and text formal dissemination; it is necessary to strengthen the check and review and standardize the management of the first issuer.

Fractional order time-delay multivariable discrete grey model for short-term online public opinion prediction

Aiming at the rapid fermentation characteristics of the online public opinion, this paper established the fractional order multivariable time-delayed discrete grey model to predict the trend of short-term online public opinion. Considering the dynamic time-varying delays of each driving factor in online public opinion, the time-delay parameters are introduced, and the lag time are determined by the maximum grey correlation theory. In order to reduce the influence of uncertainty between short-term public opinion data, the integer order accumulation is extended to the fractional order one, and the parameters are calculated by optimization model. Furthermore, the model is applied to forecast real event on microblog, and the results show that the new grey model has higher prediction accuracy compared with related grey models.

AB-LaBSE: Uyghur Sentiment Analysis via the Pre-Training Model with BiLSTM

In recent years, more and more attention has been paid to text sentiment analysis, which has gradually become a research hotspot in information extraction, data mining, Natural Language Processing (NLP), and other fields. With the gradual popularization of the Internet, sentiment analysis of Uyghur texts has great research and application value in online public opinion. For low-resource languages, most state-of-the-art systems require tens of thousands of annotated sentences to get high performance. However, there is minimal annotated data available about Uyghur sentiment analysis tasks. There are also specificities in each task—differences in words and word order across languages make it a challenging problem. In this paper, we present an effective solution to providing a meaningful and easy-to-use feature extractor for sentiment analysis tasks: using the pre-trained language model with BiLSTM layer. Firstly, data augmentation is carried out by AEDA (An Easier Data Augmentation), and the augmented dataset is constructed to improve the performance of text classification tasks. Then, a pretraining model LaBSE is used to encode the input data. Then, BiLSTM is used to learn more context information. Finally, the validity of the model is verified via two categories datasets for sentiment analysis and five categories datasets for emotion analysis. We evaluated our approach on two datasets, which showed wonderful performance compared to some strong baselines. We close with an overview of the resources for sentiment analysis tasks and some of the open research questions. Therefore, we propose a combined deep learning and cross-language pretraining model for two low resource expectations.

Research on Problems and Countermeasures of Government Response to Online Public Opinion in the Era of Self-Media

With the advent of the era of self-media, the Internet has become the most important medium for citizens to share information and express their opinions. The continuous spread and fermentation of any social developments may form online public opinion, which may have a certain guiding effect on major social issues. Therefore, governments at all levels deepen online governance and attach importance to early warning and detection of online public opinion. A comprehensive central-local online public opinion response system needs to be built urgently. Based on the Life cycle theory, the main current situation of online public opinion at present is analyzed through the case study method and the comparative research method. It is possible to identify and summarize the shortcomings of government countermeasures for online public opinion in the era of self-media, such as the failure of early warning and monitoring mechanisms of local governments, the lack of coherence between central and local government departments and the lack of administrative work in the aftermath. Based on this, I attempt to construct an optimal path for government countermeasures for online public opinion, actively implement the central government’s emphasis on public opinion governance at all levels and establish a perfect online public opinion response mechanism.

The Spread, Rise, and Fall of University Students' Interconnected Internet Public Opinion in the Age of Big Data.

With the interconnected network's quick growth and widespread adoption, it has only made sense that it would serve as a hub for the dissemination of ideologies and cultural information as well as an amplifier for public opinion. The world is dualistic. The popularity of the connected network has both positive and negative effects on society. It makes people's lives more convenient, but it also has some drawbacks. Public opinion will quickly build up on the interconnected network as network communication becomes a significant method of disseminating social information, and the number of public opinion events on the interconnected network will also rise. Accurately understanding the law of higher education students' online public opinion to effectively direct and utilise online public opinion to carry out ideological education for students and to realise the establishment of students' good values, mental health, and behavioural norms, it is necessary to understand how to spread and rise and fall in the era of big data work. The parameter inversion model of online public opinion is established in this article based on the aforementioned issues. The parameter inversion algorithm is used to calculate the trend value of online public opinion, and the degree of fitting between the trend value of actual data and the trend value of parameter inversion is compared. The study discovered that the experiment's fitting value is as high as 90%. The model's prediction of the overall trend of the event development is correct, indicating that the model parameters are inverted, even though the actual public opinion data are affected by a variety of random factors, so some deviations may occur at local points. The internal law of the evolution of events that spread public opinion has been discovered, and it can be used to accurately describe the evolution and development of the public opinion dissemination process as it is driven by its internal mechanism. In the age of big data, this article analyses and summarises the rise, fall, and distribution of online public opinion among students at institutions of higher education. It also serves as a guide for monitoring and directing online public opinion in colleges and other institutions of higher education.

Research on Internet Public Opinion of Major Conferences Based on Big Data—Take the 2021 World Internet Conference Data as an Example

By using K-means clustering method and Porter’s five forces model, taking the 2021 World Internet Conference data as an example, and with the help of big data platforms such as Baidu Index and Sina Micro Index, this paper analyzes the evolving law of online public opinion in major conferences and the heat influencing factors. Research indicates: Internet public opinion begins to fluctuate a week before the opening of major conferences, reaches its peak for the first time on the opening day, and then public opinion will rebound, until the closing of the conference, public opinion begins to weaken; during the evolution of online public opinion, the government and official media are the leading forces in handling online public opinion. Facing online public opinion of major conferences, the government should first plan ahead and respond quickly, but should not interfere excessively; secondly, give full play to the guiding role of guests and experts; give full play to the government's "three micro ends" communication channel again. The big data platform provides data support for the government to scientifically respond to the network public opinion of major conferences.

Online Public Opinion Mining for Large Cross-Regional Projects: Case Study of the South-to-North Water Diversion Project in China

Public perspective has long been ignored in ex-post evaluation of large cross-regional projects (LCPs), and the emergence of online public participation affords the opportunity to obtain and analyze public opinions from a wide range. Taking the South-to-North Water Diversion Project (SNWDP) as a typical LCP case, this study explored in depth the diverse and regionalized impacts of the project as reflected in online public opinion by developing an evaluation framework integrating post intensity, sentiment, and topic analyses. Leveraging lexicon-based sentiment analysis and latent Dirichlet allocation–based topic modeling technologies, patterns of public sentiments and topics were identified from spatial and temporal perspectives. The results showed that post intensity and public sentiment were significantly affected by project-related major events. A comparison of the water-donating and -receiving areas suggested that people in the water-receiving area had a more attentive and active attitude toward the project, and those in the water-donating area were predisposed to be more vigilant to negative events. Moreover, the variation of public sentiment across regions was found to largely depend on local social context. With regard to topic analysis, people in the water-donating and -receiving areas were more likely to focus on topics directly associated with their own interests, while the feasibility of the SNWDP garnered attention from both areas. In addition, project functions and significance as well as topical issues related to engineering corruption, water pollution, and security aroused widespread attention in all the areas under study. This study contributes to the literature on ex-post evaluation and public participation in the context of LCPs by incorporating online public opinion into the evaluation framework. The findings provide valuable insights for developing policies and strategies to improve the management of projects and to achieve an inclusive development process for projects of this type.

Research on Reputation Evaluation of Accounting Firms from the Perspective of Internet Public Opinion <br/>—Multi-Case Analysis Based on Hot Events

There are few studies on using external informal governance to improve the reputation of accounting firms, and no studies have been conducted to evaluate the reputation of accounting firms from the perspective of online public opinion. In this paper, the method of constructing model is used to analyze the influence of public opinion on the reputation of accounting firms. Therefore, from the perspective of network public opinion, based on the PSR model, this paper constructs indicators such as the pressure of network public opinion on accounting firms, the state after pressure, and the reaction of the market and CSRC to events. The study finds that negative online public opinion will change an accounting firm’s reputation indicators. Still, the timely response and high transparency of accounting firms and CSRC will effectively weaken the negative online public opinion.

Rating the Crisis of Online Public Opinion Using a Multi-Level Index System

Online public opinion usually spreads rapidly and widely, thus a small incident probably evolves into a large social crisis in a very short time, and results in a heavy loss in credit or economic aspects. We propose a method to rate the crisis of online public opinion based on a multi-level index system to evaluate the impact of events objectively. Firstly, the dissemination mechanism of online public opinion is explained from the perspective of information ecology. According to the mechanism, some evaluation indexes are selected through correlation analysis and principal component analysis. Then, a classification model of text emotion is created via the training by deep learning to achieve the accurate quantification of the emotional indexes in the index system. Finally, based on the multi-level evaluation index system and grey correlation analysis, we propose a method to rate the crisis of online public opinion. The experiment with the real-time incident show that this method can objectively evaluate the emotional tendency of Internet users and rate the crisis in different dissemination stages of online public opinion. It is helpful to realizing the crisis warning of online public opinion and timely blocking the further spread of the crisis.

Comparative Analysis and Strategy Research of Enterprises Dealing with Network Public Opinion Based on Text Mining

Enterprises need to pay attention to and track changes in online public opinion, and create a good public opinion environment for enterprise development. This study analyzes the successful experiences and deficiencies of enterprises in dealing with network public opinion, which is helpful to provide decision support for enterprises to respond to network public opinion. Two public opinion incidents of “Pinduoduo Employee's Sudden Death” and “Huolala Girl Jumps from the Car” are taken as the research objects. Based on text mining methods, the evolution of network public opinion, semantic network and sentiment trends are compared and analyzed. Through comparative analysis, it is found that Pinduoduo's comments focus on the corporate institutions and labor law, and revolve around multiple important nodes. The Huolala's comments focus on the truth and rectification of the event, and only revolve around two important nodes. The proportion of negative emotions in the early stage of the “Huolala girl jumping from the car” is much higher than that of the “Pinduoduo employee sudden death”. However, Huolala did better than Pinduoduo in terms of coping strategies, which makes the proportion of negative emotions in the later stage lower and comments tend to be more rational. This study put forward corresponding strategies and suggestions for enterprises to effectively respond to the crisis of online public opinion. Firstly, network public opinion early warning mechanism need to be established to control from the source. Secondly, companies have to understand the direction of public opinion and grasp the focus. Thirdly, companies need to strengthen responsibility awareness and have courage to take responsibility. Fourthly, follow-up management system and propose corrective measures should be carried out.