Real-time monitoring for university network public opinion information based on improved deep learning

Wireless sensor routing protocol affects the retrieval work of the system. The traditional intelligent retrieval system of network public opinion information is difficult to obtain the event probability due to the selected technology, which leads to the weak ability of the system to retrieve massive data. This paper designs an intelligent retrieval system of network public opinion information based on wireless network technology. In terms of hardware, Lucene search engine architecture and rs323 bus circuit are designed; in terms of software design, network public opinion information similarity calculation model is designed, wireless sensor routing protocol is set based on wireless network technology, and network public opinion information intelligent retrieval logic is established. In the experiment, the amount of public opinion information to be retrieved is 100, 5000 and 100000 respectively. In the same test period, when the amount of network public opinion information to be retrieved is large, the retrieval system based on wireless network technology can obtain the target information, while the amount of target information obtained by traditional system is far less than expected.KeywordsWireless network technologyNetwork public opinion informationIntelligenceRetrieval system

The network public opinion information resources include text, pictures, videos and other modes, resulting in high sharing loss value. The network public opinion information resources sharing method is based on data analysis and artificial intelligence algorithm. First, based on spatial theory, a spatial model of the emotional dimension of network public opinion big data is constructed to dynamically capture and express the multi-dimensionality and dynamism of public opinion emotions. Subsequently, advanced multimodal neural network technology was utilized to accurately identify and extract deep features of network public opinion information resources, effectively addressing data heterogeneity. Furthermore, designing and implementing a resource sharing mechanism based on semantic fusion algorithm promote efficient matching and sharing of resources through deep semantic alignment and composite semantic relationship mining. Finally, simulation tests were conducted from four aspects: data analysis, shared loss values, feature recognition effectiveness, and shared performance. The results showed that the proposed method performed well in quantitative experiments, with lower sharing loss values (about 0.01), more accurate identification of network public opinion big data features, and significantly shorter sharing completion time, average waiting time, and resource download time than the comparative methods, only 7.66 s, 2.03 s, and 5.04 s, respectively, proving its stronger sharing ability and superior performance.

Traditional public opinion information identification methods have poor performance, eitherlow accuracy, or rely on hand-designed features. This paper converts public opinion information identification to text classification problem, and proposes a public opinion information identification method based on Word2Vec and graph convolutional networks. First, Word2Vec is used to train word vector and word-article graphs are constructed; then, the graphs are trained and classified by graph convolutional neural network; finally, network public opinion information recognition is completed according to the classification results. The experimental results on the constructed Central Asian country data set show that the proposed method has achieved better performance,where the average identification accuracy of “Belt and Road” network public opinion information reached 85.58%.Furthermore, the performance on other data sets is also comparable to current mainstream text classification methods.

In physics, the process of heat conduction of objects is similar to the process of network public opinion propagation of major emergencies. Based on the theory of heat transfer, this paper analogizes the process of network public opinion information propagation and object heat conduction and analogizes the exchange of network public opinion information between individuals in social networks to the course of object heat transfer. Based on the accumulation of individual energy in social network, the propagation model of network public opinion is established, and the propagation control model of network public opinion in major emergencies is established based on the heat conduction theory. The influence of individual interest, propensity to spread, transmission coefficient of network public opinion information, and the breadth of dissemination on the dissemination of network public opinion in major emergencies are analyzed, respectively. This study provides some inspiration for the disposal and governance of network public opinion, propagation of major emergencies.

The traditional information encryption model takes advantage of the ergodicity of chaotic system, and processes encryption iteratively for many times. Aiming at the above problems, this paper constructs a big data-based network public opinion information adaptive encryption model. Reptiles are used to collect network public opinion information, and the public opinion information is replaced and diffused. After mining the association rules of public opinion information, the information is encrypted by Logistic mapping, and the encryption model is constructed. Compared with the two traditional encryption models, it is proved that the model has the advantages of good encryption effect, high efficiency and low cost, and can be used widely.

Fluctuations of investor network public opinion information evolvement were adopted as the research object in this paper. By network information capture, text classification and sentiment scoring, etc., a comprehensive index was set for network public opinion fluctuations; furthermore, an EGARCH model was utilized to perform public opinion information fluctuation fitting. As indicated by fitting results, fluctuations of investor network public opinions exhibited some characteristics of volatility clustering and asymmetry, etc. so that they were more susceptible to impacts of negative news.

Compared with the traditional media era, the network information production and dissemination mode in the new media era has undergone essential changes. Especially after the outbreak of major public health events of public concern, a variety of public opinion information spread together, and the evolution law of network public opinion becomes more complex, which easily leads to the outbreak of a public opinion crisis. Therefore, it is of great significance to master the evolution law of public opinion information about major public health events and scientifically intervene and guide public opinion for event handling and maintaining social stability, and it is also a crucial part of the field of public management at present. Based on SEIR infectious disease model, this paper analyzed the dynamic characteristics of dissemination of network public opinion information and built a simulation model using the dynamic simulation method on the NetLogo simulation platform to simulate the evolution law of network public opinion of major public health events, analyzed the expected effect of public opinion intervention and public opinion guidance strategies, and put forward a more scientific idea of public opinion intervention and public opinion guidance.

Purpose In the new era of highly developed Internet information, the prediction of the development trend of network public opinion has a very important reference significance for monitoring and control of public opinion by relevant government departments. Design/methodology/approach Aiming at the complex and nonlinear characteristics of the network public opinion, considering the accuracy and stability of the applicable model, a network public opinion prediction model based on the bald eagle algorithm optimized radial basis function neural network (BES-RBF) is proposed. Empirical research is conducted with Baidu indexes such as “COVID-19”, “Winter Olympic Games”, “The 100th Anniversary of the Founding of the Party” and “Aerospace” as samples of network public opinion. Findings The experimental results show that the model proposed in this paper can better describe the development trend of different network public opinion information, has good stability in predictive performance and can provide a good decision-making reference for government public opinion control departments. Originality/value A method for optimizing the central value, weight, width and other parameters of the radial basis function neural network with the bald eagle algorithm is given, and it is applied to network public opinion trend prediction. The example verifies that the prediction algorithm has higher accuracy and better stability.

At present, the use of public opinion analysis method to explore the feelings of users in comments has become one of the hot research topics, and has been applied in many business and public management fields, such as movie box office, stock trend prediction, public opinion monitoring in power sector, etc. Data mining and analysis based on big data technology is increasingly demanding, and the logical relationship of data processing is increasingly complex. How to analyze and mine network public opinion information in heterogeneous data environment has become a big challenge in data management, application and value mining. This paper summarizes and compares several mainstream public opinion analysis methods and their applications, including unsupervised public opinion analysis method and supervised public opinion analysis method, and introduces the application scenarios related to public opinion analysis. A network public opinion analysis system model based on big data technology is designed to provide important data support for network public opinion monitoring.

Study on Network Public Opinion Dissemination and Coping Strategies in Large Fire Disasters

With the rapid development of Internet technology, various social networking platforms, especially mobile social networking platforms, continue to increase, resulting in a large amount of public opinion information. Internet public opinion has a clear emotional orientation, and its emotional orientation is very easy to spread and be infected, and even affect the development of the event. Aiming at the characteristics of lyric information rich and which are easy to change with time, the lyric theme analysis model and the lyric emotion evolution model are proposed. The LDA model is used to extract the topic from the lyric text in a period of time, and the sensational heat value is calculated according to the forwarding amount and the number of comments, and the lyrical theme with the highest heat is obtained. The relative entropy between sub-topics in the adjacent time slice of a specific hot topic is calculated, and the degree of association between the topics in the adjacent time slice is determined, thereby analyzing whether there is a split of the sub-topic and a new topic. Then the evaluation object is extracted, combined with the joint deep neural network model to judge the emotions of each evaluation object in different time, and the emotional evolution of the hot topic is analyzed from multiple dimensions. Finally, an example analysis of the network public opinion information from June to July 2018 is carried out to verify the validity of the above model. The model effectively solves the problems of immature emotion analysis model and low accuracy of emotion classification in the current public opinion analysis.

With increasing growth of the Internet and rapid development of search engine technology, people can transmit or acquire all kinds of information that happens all the time on a variety of social media and network platforms. The network information management departments of local governments attach great importance to these online public opinions which have a certain impact on the society. The crawling of network public opinion information in Shunyi District of Beijing from Weibo is taken as an example and analyzed in this Paper for final focuses on livelihood concerns and providing reference for the situation awareness of public opinion in Shunyi District by clustering analysis on public opinion with the LDA text clustering algorithm and determination of topic characteristics of each category of public opinions.

Under the background of increasing unexpected social emergency events, this paper studied the research status of network public opinion information collection, analyzed its characteristics, container present form in unexpected social emergency, and gathering way, existing problems and causes of network public opinion information collection in social emergency. Then this paper verified information collection efficiency of network public opinion in unexpected social events, from the dimension of network public opinion fixed-point harvest engine and crawler search engines line programming tasks allocation. Static information acquisition model and crawler search engines model of network public opinion in unexpected social emergency are built.

As an important expression of social public opinion, network public opinion develops rapidly with the popularization of the internet and then affects the real society. Therefore, the use of computer technology to study the network public opinion information transmission mechanism has strong practical significance. The purpose of this paper is to use cloud computing to realize the research of information dissemination mechanism in the context of cross-media public opinion network. Researched from three aspects of operator supervision, number of media, and user density, the hotspot propagation mechanism of Storm platform given in this paper can solve the efficiency problems of traditional algorithms while ensuring accuracy, improve efficiency, and lay the foundation for the research on the monitoring of Internet public opinion propagation.

With the rapid development of social network platform, in order to purify the network environment, prevent the abuse of public opinion information, and control public opinion in a very short time, this paper proposes the application research of deep learning in social network public opinion sentiment recognition and analysis. Through the construction of social network model and social network knowledge map and the analysis of key technology, a network public opinion algorithm based on deep learning is proposed, and a competitive public opinion information communication model in online social networks is constructed, and then a simulation experiment is conducted on the improved model of the constructed social networks. The result shows that in public opinion management and control, for users with larger node degree, this technology can effectively understand and obtain public opinion information in a very short time with faster and wider information propagation speed, so as to realize the effective control of public opinion information and the processing of massive information.