Microblog Data Research Articles

Research on CO-word network topic mining and topic differences based on haze microblog data

Some studies have shown that haze not only poses a threat to people’s health, but also affects the secretion of human hormones, making people depressed and endangering mental health. Microblog has the advantages of short content, rapid communication and convenient interaction. When the haze comes, a large number of topic microblogs related to the haze will be generated. Mining the topics of concern and psychological reactions contained in these microblogs is helpful for resource allocation and public opinion publicity in the case of haze. At present, the research of microblog topic mining in haze situation only involves a single research area, and few studies discuss the spatial differences of different regions. Based on this, this study collected the microblog data of seven provincial capitals in the severe haze areas in 2017, and used the community-based co word network method to complete a series of experimental steps, such as keyword extraction, co-occurrence matrix construction, co-word network construction and topic community detection. On this basis, we detected the topic community in the microblog data set, and analyzed the horizontal differences of topics in different cities. The results show that different cities have not only the same but also different concerns about haze. The results can provide theoretical guidance for the healthy development of cities.

A hybrid semi-supervised boosting to sentiment analysis

In this article, we propose a hybrid semi-supervised boosting algorithm to sentiment analysis. Semi-supervised learning is a learning task from a limited amount of labeled data and plenty of unlabeled data which is the case in our used dataset. The proposed approach employs the classifier predictions along with the similarity information to assign label to unlabeled examples. We propose a hybrid model based on the agreement among different constructed classification model based on the boosting framework to assign a final label to unlabeled data. The proposed approach employs several different similarity measurements in its loss function to show the role of the similarity function. We further address the main preprocessing steps in the used dataset. Our experimental results on real-world microblog data from a commercial website show that the proposed approach can effectively exploit information from the unlabeled data and significantly improves the classification performance.

Enhancing Influenza Epidemics Forecasting Accuracy in China with Both Official and Unofficial Online News Articles, 2019–2020

Real-time online data sources have contributed to timely and accurate forecasting of influenza activities while also suffered from instability and linguistic noise. Few previous studies have focused on unofficial online news articles, which are abundant in their numbers, rich in information, and relatively low in noise. This study examined whether monitoring both official and unofficial online news articles can improve influenza activity forecasting accuracy during influenza outbreaks. Data were retrieved from a Chinese commercial online platform and the website of the Chinese National Influenza Center. We modeled weekly fractions of influenza-related online news articles and compared them against weekly influenza-like illness (ILI) rates using autoregression analyses. We retrieved 153,958,695 and 149,822,871 online news articles focusing on the south and north of mainland China separately from 6 October 2019 to 17 May 2020. Our model based on online news articles could significantly improve the forecasting accuracy, compared to other influenza surveillance models based on historical ILI rates (p = 0.002 in the south; p = 0.000 in the north) or adding microblog data as an exogenous input (p = 0.029 in the south; p = 0.000 in the north). Our finding also showed that influenza forecasting based on online news articles could be 1–2 weeks ahead of official ILI surveillance reports. The results revealed that monitoring online news articles could supplement traditional influenza surveillance systems, improve resource allocation, and offer models for surveillance of other emerging diseases.

Modeling collective behavior of posting microblogs by stochastic differential equation with jump

The characterization and understanding of online social network behavior is of importance from both the points of view of fundamental research and realistic application. In this manuscript, we propose a stochastic differential equation to describe the online microblogging behavior. Our analysis is based on the microblog data collected from Sina Weibo, which is one of the most popular microblogging platforms in China. Especially, we focus on the collective nature of the microblogging behavior, which embodies itself as the periodic patterns, the stochastic fluctuations around the baseline, and the extraordinary jumps in the analyzed data. Compared with existing works, we use time dependent parameters to facilitate the periodic feature of the microblogging behavior and incorporate a compound Poisson process to describe the extraordinary spikes in the Sina Weibo volume. These distinct merits lead to significant improvement in the prediction performance, thus justifying the validity of our model. This work may offer an alternative route towards the future detection of the anomalous behavior in online social network platforms.

Extracting disaster information based on Sina Weibo in China: A case study of the 2019 Typhoon Lekima

As an emerging big data source, social media data has been attracted more and more attention in the field of disaster emergency management. This study took the case of the Super Typhoon Lekima, which landed in China in 2019, to explore how the public's disaster risk perception changed during disaster response based on microblog data from Sina Weibo, commonly regarded as “Chinese Twitter”. We first analyzed characteristics of microblogs and found that microblog activities were closely related to Super Typhoon Lekima's landing process, the public could sense typhoon landfall about 72 h in advance. Second, we found that there exists a significant linear correlation between microblog counts and precipitation on a daily and provincial scale. Finally, we constructed Chinese disaster-relevant keyword sets and used Naïve Bayesian classification to calculate population-adjusted disaster score of affected-people, collapsed-house and affected-agriculture, and we found that the extracted disaster information from microblogs was corelated to real loss at provincial scale, and Weibo provide further detailed spatial distribution characteristics of Lekima's destruction. This research demonstrates that disaster information extracted form Sina Weibo could reflect the public's disaster risk perception well and have potential to serve as a data source for disaster management in China.

Managing a natural disaster: actionable insights from microblog data

ABSTRACT Social media message boards have become a critical source of information during mass emergencies/disasters, leading to appropriate human action. The use of platforms like Twitter to share information about unfolding crises and social media adoption by governments for communication has increased interest in developing rounded disaster management strategies. Although scholarly works exist for modeling human-traits as social media usage predictors, seminal works on using social media as a predictor for human behavior are rare. This paper aims to identify pertinent information communicated amidst a disaster to unearth linguistic and thematic features that make tweets popular and attract human involvement. This research is based on the calamities during the last decade in the Indian subcontinent. We apply computational intelligence to identify features that make a tweet popular during a disaster. Our research suggests that Tweet popularity attracting human action in a disaster is affected by communication style over social media.

Quantifying emotional differences in urban green spaces extracted from photos on social networking sites: A study of 34 parks in three cities in northern China

In rapid urbanization processes, the high density and fast rhythm of the urban living environment lead to mental tension, life pressure, anxiety, and other problems for people, which facilitates negative emotions. Studies have confirmed that an urban green space is a “restorative environment" that can effectively alleviate negative emotions and improve moods. Social media data can be objectively quantified to evaluate people's emotional responses to urban green spaces. Based on the analysis of social media data, this study examines whether there are differences in emotions linked to locations, with the data extracted from microblogs similar to Twitter in three different cities. Seven emotions (happiness, fear, surprise, anger, disgust, neutral, and sadness) were identified using online cognitive services on photos collected from microblog data. Three emotion-based indexes (emotion intensity index, emotion intensity index, emotion evenness index) were used to expand the urban green space pair from the spatial perspective of research on the influence of emotion. The results show that there are significant correlations among age, gender, emotional diversity, area, accessibility, NDVI, and emotion. The results also show that (1) the higher the NDVI of urban green space, the greater the probability and intensity of emotion in green space, and the more happiness emotion people show. (2) there is a significant positive correlation between urban green space area and EEI, and a significant negative correlation between urban green space area and EPI, EII, which is just opposite to the NDVI results. (3) Optimistic and positive emotions are widely expressed in cities, and happiness is expressed most and strongly. The negative emotions such as fear, anger, and trouble are less expressed, and the expressions of emotions in cities are highly similar. With the increase of age, happiness emotion increased, and sadness emotion decreased.These results show that the urban green space planning can be used to intervene in the expression of human emotion based on where a person lives. In the future, the planning and design of urban green spaces based on the reasonable balance and combinations of area, accessibility, and the NDVI can enhance the emotional enthusiasm for these areas. Improving the planning and design of the existing urban parks and green spaces with positive intervention methods can provide a feasible solution to meet the growing population's emotional recovery needs.

Online urban-waterlogging monitoring based on a recurrent neural network for classification of microblogging text

Abstract. With the global climate change and rapid urbanization, urban flood disasters spread and become increasingly serious in China. Urban rainstorms and waterlogging have become an urgent challenge that needs to be monitored in real time and further predicted for the improvement of urbanization construction. We trained a recurrent neural network (RNN) model to classify microblogging posts related to urban waterlogging and establish an online monitoring system of urban waterlogging caused by flood disasters. We manually curated more than 4400 waterlogging posts to train the RNN model so that it can precisely identify waterlogging-related posts of Sina Weibo to timely determine urban waterlogging. The RNN model has been thoroughly evaluated, and our experimental results showed that it achieved higher accuracy than traditional machine learning methods, such as the support vector machine (SVM) and gradient boosting decision tree (GBDT). Furthermore, we build a nationwide map of urban waterlogging based on recent 2-year microblogging data.

Tracing Policy-relevant Information in Social Media: The Case of Twitter before and during the COVID-19 Crisis

Abstract Real-time social media data hold great conceptual promise for research and policymaking, but also face substantial limitations and shortcomings inherent to processing re-purposed data in near-real-time. This paper aims to fill two research gaps important for understanding utility of real-time social media data for policymaking: What policy-relevant information is contained in this data and whether this information changes in periods of abrupt social, economic, and policy change. To do so, this paper focuses on two salient policy areas heavily affected by the lockdown policies responding to the 2020 COVID-19 crisis – early childhood education and care policies, and labor market policies focused on (un)employment. We utilize Twitter data for a four-month period during the first wave of COVID-19 and data for the same four-month period the preceding year. We analyze this data using a novel method combining structural topic models and latent semantic scaling, which allows us to summarize the data in detail and to test for change of content between the period of ‘normalcy’ and period of ‘crisis’. With regards to the first research gap, we show that there is policy-relevant information in Twitter data, but that the majority of our data is of limited relevance, and that the data that is relevant present some challenges and limitations. With regards to the second research gap, we successfully quantify the change in relevant information between periods of ‘normalcy’ and ‘crisis’. We also comment on the practicality and advantages of our approach for leveraging micro-blogging data in near real-time.

Public Responses to Air Pollution in Shandong Province Using the Online Complaint Data

As air users, the public is also participants in air pollution control and important evaluators of environmental protection. Therefore, understanding the public perception and response to air pollution is an essential part of improving air governance. This study proposed an analytical framework for public response to air pollution based on online complaint data and sentiment analysis. In the proposed framework, the emotional dictionary of air pollution was firstly constructed using microblog data and complaint data. Secondly, the emotional dictionary of air pollution and the sentiment analysis method were used to calculate public complaints’ emotional intensity. Besides, the spatial and temporal characteristics of air pollution complaint data and public emotional intensity, the complaints content, and their correlation with PM2.5 (particulate matters smaller than 2.5 micrometers) and PM10 were analyzed using address matching, spatial analysis, and word cloud analysis. Finally, the proposed framework was applied to 13,469 air pollution complaint data in Shandong Province from 2012 to 2018. The obtained results indicated that: the public was mainly complaining about the exhaust gas emissions from enterprises and factories. Spatially, the geographical center of complaint data was located in the inland industrial urban agglomeration of Shandong Province. Correlatively, air pollution complaints’ negative emotional intensity was significantly negatively correlated with PM2.5 (−0.73). Moreover, the number of public complaints about air pollution and the intensity of negative emotions also decreased with improved air quality in Shandong Province in recent years.

Temporal and Spatial Characteristics of Government Microblog Response to COVID-19 Epidemic in Hubei Province

Taking the government microblog data of various states and cities in Hubei Province from January 1 to March 25, 2020 as the sample, this paper uses LDA topic model and spatial analysis method to mine the implicit semantics and analyze the temporal and spatial characteristics.The results show that: (1) there is a significant positive correlation between the response of government microblog and the development of the epidemic. During the epidemic, government microblog is an important channel for the governments of various states and cities to communicate with the people;(2) The government microblog mainly includes seven implied themes, which reflect the positive actions of the government in promoting covid-19 epidemic control from the theme frequency;(3) In response to major public health emergencies, the media response of Hubei provincial government is relatively fast and the topic management is properly selected.

‘Şule Çet İçin Adalet’: Twitter Verisinin Eleştirel Söylem Çözümlemesi Modeli ile İncelenmesi

Kadın cinayetleri sadece Türkiye’de değil dünya çapında çözülmeyi bekleyen önemli bir sorundur. Kadın cinayetleri femicide kavramının Türkçe alanyazın içerisinde kullanılan en yaygın tanımıdır. Kadın cinayeti denildiğinde en basit anlamda kadının sadece kadın olduğu için öldürülmesinin ifadesidir. Bu çalışmada Şule Çet cinayeti ardından mikro-blog olan sosyal paylaşım sitesi Twitter verilerinin geriye dönük olarak taranması ve eleştirel söylem çözümlemesi ile araştırılmasını kapsamaktadır. Şule çet için adalet hastag’i ile oluşturulan mikro-bloğun incelenmesi ve analizleri sonucunda elde edilen bulgular arasında Türkiye’deki adelet sisteminin eril bir adalet olduğu, kadınların cinsel hayatlarının, bekar ve çalışıyor olmalarının, ailelerinde uzak yaşıyor olmalarının, giyim tarzlarının tecavüzü ve cinayeti meşrulaştıran kavramlar olarak görüldüğü sonuçlarına ulaşılmıştır. Yapılan incelemeler sonucunda geçtiğimiz yıllarda yine Türkiye’de işlenen tecavüz ve cinayetlere göndermeler yapılmış ve adaletin sağlanması için çağrılar yapılmıştır. Ayrıca ayrıcalıklı gruplara uygulanan cinsel tacizler de kınanmıştır.

Concerns Expressed by Chinese Social Media Users During the COVID-19 Pandemic: Content Analysis of Sina Weibo Microblogging Data.

BackgroundThe COVID-19 pandemic has created a global health crisis that is affecting economies and societies worldwide. During times of uncertainty and unexpected change, people have turned to social media platforms as communication tools and primary information sources. Platforms such as Twitter and Sina Weibo have allowed communities to share discussion and emotional support; they also play important roles for individuals, governments, and organizations in exchanging information and expressing opinions. However, research that studies the main concerns expressed by social media users during the pandemic is limited.ObjectiveThe aim of this study was to examine the main concerns raised and discussed by citizens on Sina Weibo, the largest social media platform in China, during the COVID-19 pandemic.MethodsWe used a web crawler tool and a set of predefined search terms (New Coronavirus Pneumonia, New Coronavirus, and COVID-19) to investigate concerns raised by Sina Weibo users. Textual information and metadata (number of likes, comments, retweets, publishing time, and publishing location) of microblog posts published between December 1, 2019, and July 32, 2020, were collected. After segmenting the words of the collected text, we used a topic modeling technique, latent Dirichlet allocation (LDA), to identify the most common topics posted by users. We analyzed the emotional tendencies of the topics, calculated the proportional distribution of the topics, performed user behavior analysis on the topics using data collected from the number of likes, comments, and retweets, and studied the changes in user concerns and differences in participation between citizens living in different regions of mainland China.ResultsBased on the 203,191 eligible microblog posts collected, we identified 17 topics and grouped them into 8 themes. These topics were pandemic statistics, domestic epidemic, epidemics in other countries worldwide, COVID-19 treatments, medical resources, economic shock, quarantine and investigation, patients’ outcry for help, work and production resumption, psychological influence, joint prevention and control, material donation, epidemics in neighboring countries, vaccine development, fueling and saluting antiepidemic action, detection, and study resumption. The mean sentiment was positive for 11 topics and negative for 6 topics. The topic with the highest mean of retweets was domestic epidemic, while the topic with the highest mean of likes was quarantine and investigation.ConclusionsConcerns expressed by social media users are highly correlated with the evolution of the global pandemic. During the COVID-19 pandemic, social media has provided a platform for Chinese government departments and organizations to better understand public concerns and demands. Similarly, social media has provided channels to disseminate information about epidemic prevention and has influenced public attitudes and behaviors. Government departments, especially those related to health, can create appropriate policies in a timely manner through monitoring social media platforms to guide public opinion and behavior during epidemics.

Exploring the construction and infiltration strategies of social bots in sina microblog

Nowadays, millions of people use Online Social Networks (OSNs) like Twitter, Facebook and Sina Microblog, to express opinions on current events. The widespread use of these OSNs has also led to the emergence of social bots. What is more, the existence of social bots is so powerful that some of them can turn into influential users. In this paper, we studied the automated construction technology and infiltration strategies of social bots in Sina Microblog, aiming at building friendly and influential social bots to resist malicious interpretations. Firstly, we studied the critical technology of Sina Microblog data collection, which indicates that the defense mechanism of that is vulnerable. Then, we constructed 96 social bots in Sina Microblog and researched the influence of different infiltration strategies, like different attribute settings and various types of interactions. Finally, our social bots gained 5546 followers in the 42-day infiltration period with a 100% survival rate. The results show that the infiltration strategies we proposed are effective and can help social bots escape detection of Sina Microblog defense mechanism as well. The study in this paper sounds an alarm for Sina Microblog defense mechanism and provides a valuable reference for social bots detection.

Modeling of false information on microblog with block matching and fuzzy neural network

The detection method of microblog false information has been constructed based on block matching and fuzzy neural network to improve the detection accuracy of microblog false information effectively. With this method, we can calculate the rank distance and sample entropy of microblog data according to the evaluation word rank vector of microblog false information, carry out the block matching of false information in fuzzy data set and input the characteristic quantity of microblog false information extracted into the fuzzy neural network classifier for data classification and recognition. So that it has achieved the optimized detection of false information and improved the judgment ability of false information. Finally, the key factors that affect the algorithm are deeply studied through simulation experiments according to the real data of Sina microblog, and the performance state between the proposed algorithm and Fuzzy C-means and Spectral Analysis algorithms is compared and analyzed correspondingly. The results show that the algorithm has good adaptability.

Application of microblog big data based for Web-based Communities

Microblog is a new forum to publish short text. Because of its huge user base and its convenience, it promises to be an excellent instrumentation for feeding and sustaining web-based communities. Therefore, the analysis of microblog topics is introduced and proposed as reference for correct decision making in online communities. This paper briefly introduces the collection method of microblog data and the clustering algorithm of topic classification. Then the clustering algorithm is improved, and the Storm system was introduced. The K-means algorithm before and after the improvement was simulated and analysed in the single-machine environment and Storm framework. The results show that the improved clustering algorithm has a higher classification accuracy and a lower false alarm rate both in the single-machine environment and Storm framework. Under the same clustering algorithm, the algorithm in the Storm framework has a higher classification accuracy, a lower false alarm rate and a shorter recognition time.

Microblog User Geolocation by Extracting Local Words Based on Word Clustering and Wrapper Feature Selection

Existing methods always rely on statistical features to extract local words for microblog user geolocation. There are many non-local words in extracted words, which makes geolocation accuracy lower. Considering the statistical and semantic features of local words, this paper proposes a microblog user geolocation method by extracting local words based on word clustering and wrapper feature selection. First, ordinary words without positional indications are initially filtered based on statistical features. Second, a word clustering algorithm based on word vectors is proposed. The remaining semantically similar words are clustered together based on the distance of word vectors with semantic meanings. Next, a wrapper feature selection algorithm based on sequential backward subset search is proposed. The cluster subset with the best geolocation effect is selected. Words in selected cluster subset are extracted as local words. Finally, the Naive Bayes classifier is trained based on local words to geolocate the microblog user. The proposed method is validated based on two different types of microblog data - Twitter and Weibo. The results show that the proposed method outperforms existing two typical methods based on statistical features in terms of accuracy, precision, recall, and F1-score.

Outlier knowledge management for extreme public health events: Understanding public opinions about COVID-19 based on microblog data

Based on complex adaptive system theory and information theory for investigating heterogeneous situations, this paper develops an outlier knowledge management framework based on three aspects—dimension, object, and situation—for dealing with extreme public health events. In the context of the COVID-19 pandemic, we apply advanced natural language processing (NLP) technology to conduct data mining and feature extraction on the microblog data from the Wuhan area and the imported case province (Henan Province) during the high and median operating periods of the epidemic. Our experiment indicates that the semantic and sentiment vocabulary of words, the sentiment curve, and the portrait of patients seeking help were all heterogeneous in the context of COVID-19. We extract and acquire the outlier knowledge of COVID-19 and incorporate it into the outlier knowledge base of extreme public health events for knowledge sharing and transformation. The knowledge base serves as a think tank for public opinion guidance and platform suggestions for dealing with extreme public health events. This paper provides novel ideas and methods for outlier knowledge management in healthcare contexts.

A Microblog Unbalanced Data Evolution Analysis Method Based on LDA Model

As a social network platform, Microblog has a large amount of information that can be mined. Microblog differs from static texts, which is time-sensitive, and the popularity of themes is changing with time. In addition, the popularity of Microblog varies from theme to theme, and the number of Microblogs varies greatly. Therefore, it has obvious unbalance characteristics. The traditional LDA model can not mine the theme intensity evolution process, and the theme mixing phenomenon will appear in the theme of unbalanced data mining. In view of the above problems, this paper proposes a method to analyze the theme evolution law of unbalanced Microblog data by introducing time variable. The experiment shows that the problem of theme words mixing is effectively solved after the balance treatment. The introduction of time variables can mine Microblog popularity and theme intensity evolution process.

Public opinion on MOOCs: sentiment and content analyses of Chinese microblogging data

ABSTRACT The increasing and widespread usage of social media enables the investigation of public preference using the web as a device. Public sentiment as expressed in 44,319 massive open online course (MOOCs) related microblogs from January to December 2017 was examined on Sina Weibo (the Chinese equivalent of Twitter) to obtain broad insight into how MOOCs are viewed by the public in the Chinese educational landscape. Despite the unstable upward trend of public interest in MOOCs over the past 12 months, the public opinion on MOOCs was largely positive. Content and sentiment analyses were conducted to facilitate a better understanding of what is communicated on social media. A general model of public opinions of MOOCs in China has been developed based on the findings. Individuals were classified into a threefold typology based on the sources and purposes of how this recent form of distance education was perceived. Based on the seven themes, the public views towards MOOCs were differentiated among ‘promoters’, ‘commenters’ and ‘experiencers’.Implications of the findings were also discussed.