Microblog Text Research Articles

Why they don’t trust the media: The Chinese public’s perception and evaluation of news media in the social media era, taking the Liu Xuezhou incident as an example

With the advent of the post-pandemic era characterised by increasing social uncertainty, the public is placing higher demands on the trust in news media. According to the 2023 Edelman Trust Barometer, the image of the media in the public’s mind is deteriorating. Why don’t they trust the media? What are the reasons given by the public when the media is denounced as unscrupulous? Taking the Liu Xuezhou incident as a typical case, the study extracts key elements from 5,225 related microblog texts, identifies the main topics of public discussion with the help of LDA topic modelling, clarifies the referential dimension of unscrupulous media with the help of pointwise mutual information, and analyzes netizens’ evaluations related to different referential levels of the media through visual semantic networks, which can help formulate dialectical thinking on media trust in the context of China in the era of social media.

A new perspective to understand public response to the Typhoon Doksuri from coastal and inland regions

Massive amounts of data from social media possess the potential to rapidly identify the primary issues of concern in emergency disaster management. In summer 2023, Super Typhoon Doksuri which was an exceptionally special typhoon disaster that caused severe damage to China's coastal areas and disastrous impacts in inland regions, particularly triggered the most severe rainstorm in Beijing area in over a century. To enhance typhoon hazard reduction in both coastal and interior locations, it is crucial to examine public response to these events. This study uses microblog text data from July 27 to August 3 of 2023 to map the public response to Typhoon Doksuri. The Support Vector Machine (SVM) algorithm was used to classify the microblog text in combination with the typhoon path to analyze the spatial and temporal variations of the emotions of the affected individuals. The relationship between changes in public opinion, the distribution of topics, and the major disasters triggered by the residual circulation of Typhoon Doksuri in the Beijing-Tianjin-Hebei region is discussed. The Mentougou mega-storm in Beijing area that occurred in July 2023 is a typical case. The findings demonstrate that during the typhoon event, the focus of public attention changed with the movement of the typhoon path, and various public opinion topics exhibited temporal synchronization. Public sentiment indicates that the overall supportive sentiment is higher than is fearful sentiment. Based on this, it is crucial to strengthen the Beijing-Tianjin-Hebei cooperative emergency response, and response measures were proposed related to urban flood control and drainage construction, public awareness, backward areas, secondary disasters, resident relocation, and social media technology.

Time varying characteristics of factors affecting carbon price in emission trading scheme in China: Evidence from SV-TVP-VAR approach

Analysis of the factors influencing the price of carbon emissions trading in China and its time-varying characteristics is essential for the smooth operation of the carbon trading system. We analyse the time-varying effects of public concern, degree of carbon regulation, crude oil price, international carbon price and interest rate level on China’s carbon price through SV-TVP-VAR model. Among them, the quantification of public concern and the degree of carbon emission regulation is based on microblog text and government decisions. The results show that all the factors influencing carbon price are significantly time-varying, with the shocks of each factor on carbon price rising before 2019 and turning significantly thereafter. The short-term shock effect of each factor is more significant compared to the medium- and long-term, and the effect almost disappears at a lag of six months. Thanks to public environmental awareness, low-carbon awareness and the progress of carbon market management mechanisms, public concern has had the most significant impact on carbon price since 2019. With the promulgation of relevant management measures for the carbon market, relevant regulations on carbon emission accounting, financing constraints, and carbon emission quota allocation for emission-controlled enterprises have become increasingly mature, and carbon price signals are more sensitive to market information. The above findings provide substantial empirical evidence for all stakeholders in the market, who need to recognize that the impact of non-structural factors on the price of carbon varies over time. Government intervention also serves as a key aspect of carbon emission control and requires the introduction of relevant constraints and incentives. In particular, emission-controlling firms need to focus on the policy direction of the carbon market, and focus on the impact of Internet public opinion on business production while reducing carbon allowance demand and energy dependence.

Triplétoile: Extraction of knowledge from microblogging text

Numerous methods and pipelines have recently emerged for the automatic extraction of knowledge graphs from documents such as scientific publications and patents. However, adapting these methods to incorporate alternative text sources like micro-blogging posts and news has proven challenging as they struggle to model open-domain entities and relations, typically found in these sources. In this paper, we propose an enhanced information extraction pipeline tailored to the extraction of a knowledge graph comprising open-domain entities from micro-blogging posts on social media platforms. Our pipeline leverages dependency parsing and classifies entity relations in an unsupervised manner through hierarchical clustering over word embeddings. We provide a use case on extracting semantic triples from a corpus of 100 thousand tweets about digital transformation and publicly release the generated knowledge graph. On the same dataset, we conduct two experimental evaluations, showing that the system produces triples with precision over 95% and outperforms similar pipelines of around 5% in terms of precision, while generating a comparatively higher number of triples.

Microblog sentiment analysis method using BTCBMA model in Spark big data environment

Abstract Microblogs are currently one of the most well-liked social platforms in China, and sentiment analysis of microblog texts can help further analyze the realization of their media value; however, the current task of sentiment analysis based on microblog information suffers from low accuracy due to the large size and high redundancy of microblog data, a microblog sentiment analysis method using Bidirectional Encoder Representation from Transformers (BERT)–Text Convolutional Neural Network (TextCNN)–Bidirectional Gate Recurrent Unit (BiGRU)–Multihead-Attention model in Spark big data environment is proposed. First, the Chinese pre-trained language model BERT is used to convert the input data into dynamic character-level word vectors; then, TextCNN is used to effectively obtain local features such as keywords and pool the filtered features; then, BiGRU is introduced to quickly capture more comprehensive semantic information; finally, a multi-headed attention mechanism is implemented to emphasize the most significant features in order to accomplish the sentiment classification of microblog information task precisely. By comparing the existing advanced models, the proposed model demonstrates an improvement of at least 4.99% and 0.05 in accuracy and F1-score evaluation indexes, respectively. This enhancement significantly enhances the accuracy of microblog sentiment analysis tasks and aids pertinent authorities in comprehending the inclination of individual’s attitude toward hot topics. Furthermore, it facilitates a prompt prediction of topic trends, enabling them to guide public opinion accordingly.

A Study of Changes in College English Online Phrases Supported by Clustering Algorithm

Abstract The hyperlinks on the Sina Weibo platform are tracked by a web crawler so as to obtain the textual resources of university English online phrases on the platform. To process microblog text data, this paper proposes the use of multiple linguistic expressions of translation machines to enhance the text feature representation and apply it to clustering to enhance the clustering results. Based on commonly used algorithms such as K-means, DBSCAN, and hierarchical clustering, we analyze the clustering effect of each algorithm according to internal and external evaluation indexes and finally determine the clustering algorithms to be used for the change of university English network terms. Using the English network word “hand” as an example, this paper observes a fluctuating trend in the heat of this word from January to June 2023, with peaks in heat generation in January and February, respectively, and a peak heat of about 10,500 in February. In terms of spatial variation, the heat level of the English word “hand” is high in the east and south regions and low in the west and north regions, but in February, due to the return of the population to their hometowns for the Lunar New Year, the north region exceeds the east and south regions with a heat level of 11086.77.

Transmission mechanism of public concern in waste-sorting policy: Evidence from text mining

An escalating amount of urban waste poses a significant threat to the sustainable growth of cities. Therefore, a waste-sorting policy is crucial for the advancement of humankind. The implementation of a waste-sorting policy relies heavily on public participation to ensure effective governance. This study examines public participation in urban waste-sorting by mining more than 580,000 microblog texts related to waste-sorting from 2012 to 2022, using data from Sina Weibo, China's leading social media platform. My findings indicate that (1) residents’ attention to and support for mandatory waste-sorting policies varies by region; (2) widespread public interest stimulates publicity, education, and commercial entertainment related to waste-sorting policies and investment in thematically related sectors; (3) residents in regions with high education and income levels are more likely to generate waste and pay greater attention to waste-sorting policies; and (4) the promotion of waste-sorting policies affects knowledge dissemination. This study combines textual analysis and econometric techniques to offer a fresh perspective on the significance of public participation in promoting waste-sorting policies. It serves as an invaluable resource for governments to implement waste-sorting policies.

A MapReduce-based approach to social network big data mining

The rapid development of social networks has facilitated the convenience of users to receive information. As a network communication platform for people’s daily use, microblog has countless information data. In view of the low efficiency and poor clustering effect of K-means algorithm, a parallel K-means clustering algorithm based on MapReduce model is studied; In order to alleviate the difficulty in calculating the similarity of microblog topic text, the space vector model and semantic similarity are used to calculate the similarity between texts to improve the quality of microblog text classification. The data expansion rate of corresponding nodes under different data sets shows that the average expansion rate of the parallel K-means algorithm reaches 0.89, and the running rate is the highest. The results show that the parallel K-means algorithm has good clustering stability and the highest clustering quality, reaching 1.24; The clustering time of the algorithm is the shortest, the average clustering time is 1.27 minutes, and the clustering effect and efficiency of the algorithm are the best. In the quality analysis of Weibo topic recommendation, the accuracy of P-K-means recommendation is 95.64%, user satisfaction is 98.64%, and the recommendation effect is also the best. It shows that the research on the parallel K-means clustering algorithm based on MapReduce has the best performance in microblogging topic mining and recommendation, which can efficiently recommend topics of interest to users and enhance users’ microblogging experience.

Research on the Classification Methods of Social Bots

In order to ensure the healthy development of social networks and the harmony and stability of the society, as well as to facilitate effective supervision by regulatory authorities, a classification method of social bots is proposed based on the identification of social bots in the early stage. First of all, the topic-related introduction is used to expand the topic, and on this basis, the SBERT (Sentence-BERT) model is applied to make relevance judgments between the micro-blog text and the expanded topics to identify polluters. Then, an opinion sentence recognition method that combines social bots opinion sentence generation rules with a deep learning model TextCNN is proposed to further distinguish commenters and spreaders. Finally, in order to improve the classification effect of the model, the transfer learning method is used to train the model with the help of a large number of micro-blogs of ordinary Weibo accounts, so as to better improve the classification effect of social bots. The comparative experimental results show that the topic expansion method can effectively improve the classification results of the SBERT model for the relevance of micro-blog text topics. When the parameter k of the expanded topic model is set at 20, the content of the expanded topic sequence is more consistent with the core content of most Weibo text sequences, and the obtained model has the best performance. By analyzing the opinion-based micro-blog text generation rules of social bots, focusing on the keywords that express opinions, the problem of difficulty in recognizing opinion sentences produced by the low quality of opinion sentences of social bots is well resolved, and the recognition effect of opinion sentences has been improved by more than 10%. Through the introduction of transfer learning, the problem of insufficient social bots data is effectively alleviated, and the classification effect of social bots is greatly improved, with an increase of more than 10%.

Understanding the role of social media sentiment in identifying irrational herding behavior in the stock market

This study examined the role of social media sentiment in identifying irrational herding behavior in the stock market. We selected the Chinese stock market, where majority are retail investors, as the object of analysis, and analyzed the sentiment of 227,353 microblog text messages through deep learning techniques and constructed the identification method of herd behavior. Results show that social media sentiment has a significant impact on irrational herding behavior in the stock market. The findings of the study complement the theory of investor behavior and can aid in investors' trading decisions and financial regulators’ policy recommendations.

Recommendation Method Based on Heterogeneous Information Network and Multiple Trust Relationship

A recommendation method based on heterogeneous information networks and multiple trust relationships is proposed. Firstly, the node sequence in the heterogeneous information network is obtained through the random walk of the meta-path, and the representation vector of each node in different paths is generated. The user similarity based on the meta-path is obtained by calculating the spatial distance between the user node vectors. Then, according to the different relationships among users, different trust-relationship calculation methods are proposed, and the user similarity based on the user’s multiple trust relationship is obtained by fusing multiple trust relationships. Finally, the candidate list of Microblog text is obtained by fusing the two user similarities to achieve a personalized recommendation of Microblog text. The experimental results show that the method proposed in this study is superior to other comparison algorithms in precision, recall, F1 value and NDCG value, which shows that this method is feasible when recommending Microblog text.

Automatic anxiety recognition method based on microblog text analysis.

Mental health has traditionally been assessed using a self-report questionnaire. Although this approach produces accurate results, it has the disadvantage of being labor-intense and time-consuming. This study aimed to extract original text information published by users on the social media platform (Sina Weibo). A machine learning method was used to train the model and predict the anxiety state of the user automatically. Data of 1,039 users were collected. First, Weibo users were invited to fill the anxiety self-assessment scale. All original text data ever published by the users were collected. Second, the Simplified Chinese-Linguistic Inquiry and Word Count (SC-LIWC) were extracted for feature selection and model training. We found that the model achieved the best performance when the XGBoostRegressor algorithm was used. The Pearson correlation coefficient between the model predicted scores and self-reported scores was moderate (r = 0.322). In addition, we tested the reliability of the model, and found that the model had high reliability (r = 0.72). The experimental results further showed that the model was feasible and effective and could use the digital footprints to predict psychological characteristics.

Mental time travel ability influences the representation of events and emotional expressions: evidence from microblogs

Mental time travel (MTT) ability allows people to project themselves mentally into the past and future. It is associated with people’s mental representation of events and objects. Using text analysis methods, we explore the linguistic representation and emotional expression of people with various MTT abilities. In Study 1, we assessed the users’ MTT distances, text lengths, visual perspectives, priming effects of temporal words, and emotional valences by analyzing 2973 users’ microblog texts. From our statistical analysis findings, users with far MTT incorporated longer text length and more third-person pronouns in their microblogs and are more likely to relate the future and past with the present than people with near MTT. However, the study showed no significant difference in emotional valence between people with different MTT distances. In Study 2, we explored the relationship between emotional valence and MTT ability by analyzing the comments of 1112 users on “procrastination.” We found the users with far MTT more positive toward procrastination than those with near MTT. By analyzing users’ social media platform data, this study re-examined and verified previous findings indicating that users who mentally travel different temporal distances represent events and emotional expressions differently. This study serves as an important reference for MTT studies.

Microblog Emotion Analysis Using Improved DBN Under Spark Platform

In order to solve the problems that traditional single-machine methods find it difficult to complete the task of emotion classification quickly, and the time efficiency and scalability are not high; a microblog emotion analysis method using improved deep belief network (DBN) under Spark platform is proposed. First, the Hadoop distributed file system is used to realize the distributed storage of text data, and the preprocessed data and emotion dictionary are converted into word vector representation based on the continuous bag-of-words model. Then, an improved DBN model is constructed by combining the adaptive learning method of DBN with the active learning method, and it is applied to the learning analysis of text word vectors. Finally, the data parallel optimization of the improved DBN model is realized, based on Spark platform to accurately and quickly obtain the emotion types of microblog texts. The experimental analysis of the proposed method based on the microblog text data set shows that the classification accuracy is more than 94%.

Microblog Text Emotion Classification Algorithm Based on TCN-BiGRU and Dual Attention

Microblog is an important platform for mining public opinion, and it is of great value to conduct emotional analysis of microblog texts during the current epidemic. Aiming at the problem that most current emotional classification methods cannot effectively extract deep text features, and that traditional word vectors cannot dynamically obtain the semantics of words according to their context, which leads to classification bias, this research put forward a microblog text emotion classification algorithm based on TCN-BiGRU and dual attention (TCN-BiGRU-DATT). First, the vector representation of the text was obtained using ALBERT. Second, the TCN and BiGRU networks were used to extract the emotional information contained in the text through dual pathway feature extraction, to efficiently obtain the deep semantic features of the text. Then, the dual attention mechanism was introduced to allocate the global weight of the key information in the semantic features, and the emotional features were spliced and fused. Finally, the Softmax classifier was applied for emotion classification. The findings of a comparative experiment on a set of microblog text comments collected throughout the pandemic revealed that the accuracy, recall, and F1 value of the emotion classification method proposed in this paper reached 92.33%, 91.78%, and 91.52%, respectively, which was a significant improvement compared with other models.

Efficient Storage Management for Social Network Events Based on Clustering and Hot/Cold Data Classification

Social network events are related to the national economy and people’s livelihood, so timely perception and processing of massive social network events data are becoming increasingly important for public opinion analysis. How to fully exploit the access feature of event information to store and manage social network events is of great significance for accurate and real-time query analysis. We propose a social network event storage management method based on microblog text clustering and hot/cold data classification. First, for the microblog text data, we construct a keyword provenance graph by using the information entropy to measure the weight of the edge between keyword nodes. Then, we cluster the events using the provenance-based community partition (PCP) with local modularity to improve the event clustering accuracy. In addition, we can further filter noisy data via incremental clustering, enable hot/cold event data classification and dynamic migration, and compress cold data to save space on a hybrid storage architecture. The experimental results show that the clustering purity can reach more than 93% and the query time can be reduced by more than 70% using clustering and hybrid storage policy.

A Study of Public Attitudes toward Shanghai's Image under the Influence of COVID-19: Evidence from Comments on Sina Weibo.

With the advent of the Internet era, Chinese users tend to choose to express their opinions on social media platforms represented by Sina Weibo. The changes in people's emotions toward cities from the microblogging texts can reflect the image of cities presented on mainstream social media, and thus target a good image of cities. In this paper, we collected microblog data containing "Shanghai" from 1 January 2019 to 1 September 2022 by Python technology, and we used three methods: Term Frequency-Inverse Document Frequency keyword statistics, Latent Dirichlet Allocation theme model construction, and sentiment analysis by Zhiwang Sentiment Dictionary. We also explore the impact of the COVID-19 epidemic on Shanghai's urban image in the context of the "Shanghai Territorial Static Management", an important public opinion topic during the COVID-19 epidemic. The results of the study show that the "Shanghai-wide static management" of COVID-19 epidemic has significantly reduced the public's perception of Shanghai and negatively affected the city's image. By analyzing the data results, we summarize the basic characteristics of Shanghai's city image and provide strategies for communicating Shanghai's city image in the post-epidemic era.

Changes in public travel willingness in the post-COVID-19 era: Evidence from social network data

<abstract> <p>Amid the impact of COVID-19, the public's willingness to travel has changed, which has had a fundamental impact on the ridership of urban public transport. Usually, travel willingness is mainly analyzed by questionnaire survey, but it needs to reflect the accurate psychological perception of the public entirely. Based on Weibo text data, this paper used natural language processing technology to quantify the public's willingness to travel in the post-COVID-19 era. First, web crawler technology was used to collect microblog text data, which will discuss COVID-19 and travel at the same time. Then, based on the Naive Bayes classification algorithm, travel sentiment analysis was carried out on the data, and the relationship between public travel willingness and urban public transport ridership was analyzed by Spearman correlation analysis. Finally, the LDA topic model was used to conduct content topic research on microblog text data during and after COVID-19. The results showed that the mean values of compelling travel emotion were -0.8197 and -0.0640 during and after COVID-19, respectively. The willingness of the public to travel directly affects the ridership of urban public transport. Compared with the COVID-19 period, the public's fear of travel infection in the post-COVID-19 era has significantly improved, but it still exists. The public pays more attention to the level of COVID-19 prevention and control and the length of travel time on public transport.</p> </abstract>

Gender Differences in Emotional Valence and Social Media Content Engagement Behaviors in Pandemic Diaries: An Analysis Based on Microblog Texts.

The effects of the COVID-19 pandemic are individualized, which means that our emotions and behaviors would experience changes of different degrees. These changes have led to subtle connections within the social media context. This study concentrates on pandemic diaries posted on microblog sites during the lockdown period in China and explores the association between gender, emotional valence in diaries, and social media content engagement behaviors. Through computational methods, this study found that males and females tended to present significantly different emotional valence and social media content engagement behaviors. A negative correlation existed between emotional valence and comment behavior in female diary texts. Moreover, the pandemic proximity had a moderating effect on emotional valence and social media content engagement behaviors. This article attempts to explain the emotional and behavioral characteristics related to social media diaries and express concerns for the emotional health of disadvantaged blog users in the severely affected area during the pandemic.

A Multi-label Classification of Disaster-Related Tweets with Enhanced Word Embedding Ensemble Convolutional Neural Network Model

Recently, automating the detection and classification of tweets using machine learning methods has been a tremendous help in crises. Word embeddings are the most effective word vectors for NLP processing using deep learning classifiers. This research proposes a novel method with the Enhanced Embedding from Language Model (EnELMo) for classifying tweets as different categories with higher classification accuracy and precision for the rapid rescue action in the disaster scenario. The proposed EWECNN method comprises an Enhanced ELMo module to handle Crisis word vectors, a Novel ELMo-CNN Architecture module for feature extraction (ECA), and an effective multi-label classification of text using Crisis Word Vector specific CNN-RNN(CWV-CRNN) stacks. Each of these functional modules is purportedly designed to improve the classification. Among the various approaches discussed, the proposed method outperforms the classification of microblog texts with the accuracy as 93.46 percent and the F1-Score as 92.99 percent for multi-classification of tweets which is higher compared with other methods. The proposed multi-label classification of disaster-related text facilitates faster rescue action in a crisis scenario