Weibo Dataset Research Articles

Social Network Public Opinion Analysis Using BERT-BMA in Big Data Environment

The existing social network public opinion analysis methods have problems such as poor semantic expression quality and weak detection ability in short texts. Therefore, a social network public opinion analysis method based on BERT-BMA is proposed. To normalize the comment text, the rumor text is initially transferred to a word vector matrix using the BERT (Bidirectional Encoder Representations from Transformer) model. The BiLSTM-based network architecture is subsequently employed to acquire the trace features of data transmission. Ultimately, this study employs the multi-head attention mechanism to extract feature information that is more significant in the analysis of online public opinion by mining the dependency relationships between users, resulting in increasing ability to detect public opinion emergencies. The experimental outcomes indicate that the results on the Twitter data set and Weibo dataset are superior to other comparative models.

The Impact of Scale on Extracting Individual Mobility Patterns from Location-Based Social Media.

Understanding human movement patterns is crucial for comprehending how a city functions. It is also important for city planners and policymakers to create more efficient plans and policies for urban areas. Traditionally, human movement patterns were analyzed using origin-destination surveys, travel diaries, and other methods. Now, these patterns can be identified from various geospatial big data sources, such as mobile phone data, floating car data, and location-based social media (LBSM) data. These extensive datasets primarily identify individual or collective human movement patterns. However, the impact of spatial scale on the analysis of human movement patterns from these large geospatial data sources has not been sufficiently studied. Changes in spatial scale can significantly affect the results when calculating human movement patterns from these data. In this study, we utilized Weibo datasets for three different cities in China including Beijing, Guangzhou, and Shanghai. We aimed to identify the effect of different spatial scales on individual human movement patterns as calculated from LBSM data. For our analysis, we employed two indicators as follows: an external activity space indicator, the radius of gyration (ROG), and an internal activity space indicator, entropy. These indicators were chosen based on previous studies demonstrating their efficiency in analyzing sparse datasets like LBSM data. Additionally, we used two different ranges of spatial scales-10-100 m and 100-3000 m-to illustrate changes in individual activity space at both fine and coarse spatial scales. Our results indicate that although the ROG values show an overall increasing trend and the entropy values show an overall decreasing trend with the increase in spatial scale size, different local factors influence the ROG and entropy values at both finer and coarser scales. These findings will help to comprehend the dynamics of human movement across different scales. Such insights are invaluable for enhancing overall urban mobility and optimizing transportation systems.

MFAE: Multimodal Fusion and Alignment for Entity-level Disinformation Detection

Nowadays, the dissemination of disinformation on social media has evolved from a purely textual form to multiple modalities consisting of both text and images. This further amplifies the misleading and deceptive nature of disinformation. Overcoming the misleading and confusing noise to achieve accurate disinformation detection presents a significant challenge. To address this challenge, we propose a method named Multimodal Fusion and Alignment for Entity-level Disinformation Detection (MFAE). MFAE first uses an improved dynamic routing algorithm to extract more comprehensive semantic visual entity features. Then, a graph matching network is used to capture the correspondences between entities within modalities. The experiment shows that MFAE is capable of capturing textual and visual semantic information more comprehensively. On the TWITTER and WEIBO datasets, MFAE achieves accuracy improvements of approximately 2.0% and 7.5%, respectively, compared to the state-of-the-art methods, resulting in accuracy of 89.5% and 96.7%.

SENTIMENT ANALYSIS OF WEIBO COMMENTS BASED ON CONVOLUTIONAL NEURAL NETWORK

Sentiment analysis of social media comments plays a crucial role in understanding public opinion and sentiment trends. This study focuses on sentiment analysis of Weibo comments, a popular microblogging platform in China, using a (CNN) approach. We propose a novel methodology that leverages the inherent structural dependencies among comments and users in the Weibo network to capture nuanced sentiment patterns. By representing Weibo comments as a graph, with users and comments as nodes and their interactions as edges, we exploit the relational information to enhance sentiment classification accuracy. Furthermore, we employ attention mechanisms to prioritize influential users and comments in the sentiment analysis process. Through extensive experiments on real Weibo datasets, our proposed CNN-based sentiment analysis framework demonstrates superior performance compared to traditional methods, achieving high accuracy in sentiment classification tasks. This research contributes to advancing sentiment analysis techniques in social media platforms and provides valuable insights for understanding public sentiment dynamics in online communities like Weibo.

Predicting viral rumors and vulnerable users with graph-based neural multi-task learning for infodemic surveillance

In the age of the infodemic, it is crucial to have tools for effectively monitoring the spread of rampant rumors that can quickly go viral, as well as identifying vulnerable users who may be more susceptible to spreading such misinformation. This proactive approach allows for timely preventive measures to be taken, mitigating the negative impact of false information on society. We propose a novel approach to predict viral rumors and vulnerable users using a unified graph neural network model. We pre-train network-based user embeddings and leverage a cross-attention mechanism between users and posts, together with a community-enhanced vulnerability propagation (CVP) method to improve user and propagation graph representations. Furthermore, we employ two multi-task training strategies to mitigate negative transfer effects among tasks in different settings, enhancing the overall performance of our approach. We also construct two datasets with ground-truth annotations on information virality and user vulnerability in rumor and non-rumor events, which are automatically derived from existing rumor detection datasets. Extensive evaluation results of our joint learning model confirm its superiority over strong baselines in all three tasks: rumor detection, virality prediction, and user vulnerability scoring. For instance, compared to the best baselines based on the Weibo dataset, our model makes 3.8% and 3.0% improvements on Accuracy and MacF1 for rumor detection, and reduces mean squared error (MSE) by 23.9% and 16.5% for virality prediction and user vulnerability scoring, respectively. Our findings suggest that our approach effectively captures the correlation between rumor virality and user vulnerability, leveraging this information to improve prediction performance and provide a valuable tool for infodemic surveillance.

Social Network Rumor Detection Method Combining Dual-Attention Mechanism With Graph Convolutional Network

Most rumor detection methods extract the features of rumor through two aspects of text semantics and propagation structure to achieve automatic rumor classification, while most of the existing methods do not realize that false and irrelevant interactions in the propagation structure will reduce the accuracy of rumor detection. In addition, most of the existing rumor detection methods failed to effectively extract key clues from the comments of social network users. In response to these phenomena, this article proposes a social network rumor detection method combining a dual attention mechanism and graph convolutional network (GCN) (dual-attention GCN, DA-GCN). First, build an event propagation graph; then, the GCN is used to extract the propagation structure information of each event-related microblog (tweet), and the attention mechanism is combined to suppress the false and irrelevant interactive relationships. Therefore, the anti-interference propagation structure features are extracted from the propagation graph. Second, to fully utilize the clues in users’ comments, this article makes use of the attention mechanism to fuse source microblog (tweet) with the comment–retweet information and extract interactive semantic features from it. Finally, the above two features are fused to generate a new event representation. Experimental results show that the proposed DA-GCN has an accuracy of 94.4%, 90.5%, and 90.2% on the Weibo dataset, the Twitter15 dataset, and the Twitter16 dataset, respectively, and has achieved excellent performance in the early rumor detection task, which proves that the proposed method is reasonable and effective.

Centrifugal Navigation-Based Emotion Computation Framework of Bilingual Short Texts with Emoji Symbols

Heterogeneous corpora including Chinese, English, and emoji symbols are increasing on platforms. Previous sentiment analysis models are unable to calculate emotional scores of heterogeneous corpora. They also struggle to effectively fuse emotional tendencies of these corpora with the emotional fluctuation, generating low accuracy of tendency prediction and score calculation. For these problems, this paper proposes a Centrifugal Navigation-Based Emotional Computation framework (CNEC). CNEC adopts Emotional Orientation of Related Words (EORW) to calculate scores of unknown Chinese/English words and emoji symbols. In EORW, t neighbor words of the predicted sample from one element in the short text are selected from a sentiment dictionary according to spatial distance, and related words are extracted using the emotional dominance principle from the t neighbor words. Emotional scores of related words are fused to calculate scores of the predicted sample. Furthermore, CNEC utilizes Centrifugal Navigation-Based Emotional Fusion (CNEF) to achieve the emotional fusion of heterogeneous corpora. In CNEF, how the emotional fluctuation occurs is illustrated by the trigger angle of centrifugal motion in physical theory. In light of the corresponding relationship between the trigger angle and conditions of the emotional fluctuation, the fluctuation position is determined. Lastly, emotional fusion with emotional fluctuation is carried out by a CNEF function, which considers the fluctuation position as a significant position. Experiments demonstrate that the proposed CNEC effectively computes emotional scores for bilingual short texts with emojis on the Weibo dataset collected.

EDRN-based propagation model for popular microblog information detection

Microblogging platforms have become popular for sharing knowledge and communicating with others. Rumours and current trends can be identified promptly if popular information trends on these platforms can be detected in the early stages of dissemination. Microblog information propagation is primarily based on forwarders; the forwarded information is more likely to become popular if the forwarder's influence is greater and the time interval between two adjacent forwarders is shorter. Based on the explicit duration recurrent network (EDRN), a recurrent neural network, a new microblog information-propagation model for the early detection of popular information was presented. In this model, the observation is constructed based on the forwarder's influence level and the time interval between two adjacent forwarders. The influence level of the forwarder was estimated using the support vector machine classifier. To evaluate this model, experiments were conducted using Twitter and Weibo datasets. In the experiments, EDRN outperformed several popular recurrent neural networks, hidden semi-Markov models, and hidden Markov models, particularly when the training set was small. The timeliness evaluation results demonstrated that the model can effectively detect popular information at an early stage.

Are Fake Images Bothering You on Social Network? Let Us Detect Them Using Recurrent Neural Network

Nowadays, social media platforms play a significant role in real-world events, which can cause both positive and negative effects. The popularity of image-based content on social media has been dramatically increased, which brings the problem that the quality of content is rather spotty. Therefore, automated techniques of identifying fake images have drawn significant attention. The traditional detection methods focus on the elements’ consistency of the image, which requires massive computing resources and huge datasets for pairs of real and fake images. Many studies on detecting rumors on social media showed that there are propagation patterns for the spreading of fake content that can be used as clues of detection. Thus, the proposed approach attempts to characterize the propagation patterns of fake images on social media using several user features and tweet features. The detection model applies recurrent neural networks to capture the variation of suggested features along the propagation path over time. The results of the experiment on a Weibo dataset of image tweets show that the model can achieve 89% accuracy in classifying fake images from real ones. Moreover, the model already reaches high performance as the detection deadline is smaller than 24 h, which demonstrates the strong capability of early detection. The positive outcomes indicate that the proposed detection model has great potential to be further developed to an automated technique that can be used in classifying real images from fake images posted on social media.

Improving Chinese Named Entity Recognition by Interactive Fusion of Contextual Representation and Glyph Representation

Named entity recognition (NER) is a fundamental task in natural language processing. In Chinese NER, additional resources such as lexicons, syntactic features and knowledge graphs are usually introduced to improve the recognition performance of the model. However, Chinese characters evolved from pictographs, and their glyphs contain rich semantic information, which is often ignored. Therefore, in order to make full use of the semantic information contained in Chinese character glyphs, we propose a Chinese NER model that combines character contextual representation and glyph representation, named CGR-NER (Character–Glyph Representation for NER). First, CGR-NER uses the large-scale pre-trained language model to dynamically generate contextual semantic representations of characters. Secondly, a hybrid neural network combining a three-dimensional convolutional neural network (3DCNN) and bi-directional long short-term memory network (BiLSTM) is designed to extract the semantic information contained in a Chinese character glyph, the potential word formation knowledge between adjacent glyphs and the contextual semantic and global dependency features of the glyph sequence. Thirdly, an interactive fusion method with a crossmodal attention and gate mechanism is proposed to fuse the contextual representation and glyph representation from different models dynamically. The experimental results show that our proposed model achieves 82.97% and 70.70% F1 scores on the OntoNotes 4 and Weibo datasets. Multiple ablation studies also verify the advantages and effectiveness of our proposed model.

Prediction and Classification of User Activities Using Machine Learning Models from Location-Based Social Network Data

The current research has aimed to investigate and develop machine-learning approaches by using the data in the dataset to be applied to classify location-based social network data and predict user activities based on the nature of various locations (such as entertainment). The analysis of user activities and behavior from location-based social network data is often based on venue types, which require the input of data into various categories. This has previously been done through a tedious and time-consuming manual method. Therefore, we proposed a novel approach of using machine-learning models to extract these venue categories. In this study, we used a Weibo dataset as the main source of research and analyzed machine-learning methods for more efficient implementation. We proposed four models based on well-known machine-learning techniques, including the generalized linear model, logistic regression, deep learning, and gradient-boosted trees. We designed, tested, and evaluated these models. We then used various assessment metrics, such as the Receiver Operating Characteristic or Area Under the Curve, Accuracy, Recall, Precision, F-score, and Sensitivity, to show how well these methods performed. We discovered that the proposed machine-learning models are capable of accurately classifying the data, with deep learning outperforming the other models with 99% accuracy, followed by gradient-boosted tree with 98% and 93%, generalized linear model with 90% and 85%, and logistic regression with 86% and 91%, for multiclass distributions and single class predictions, respectively. We classified the data using our machine-learning models into the 10 classes we used in our previous study and predicted tourist destinations among the data to demonstrate the effectiveness of using machine learning for location-based social network data analysis, which is vital for the development of smart city environments in the current technological era.

Kcr-FLAT: A Chinese-Named Entity Recognition Model with Enhanced Semantic Information.

The performance of Chinese-named entity recognition (NER) has improved via word enhancement or new frameworks that incorporate various types of external data. However, for Chinese NER, syntactic composition (in sentence level) and inner regularity (in character-level) have rarely been studied. Chinese characters are highly sensitive to sentential syntactic data. The same Chinese character sequence can be decomposed into different combinations of words according to how they are used and placed in the context. In addition, the same type of entities usually have the same naming rules due to the specificity of the Chinese language structure. This paper presents a Kcr-FLAT to improve the performance of Chinese NER with enhanced semantic information. Specifically, we first extract different types of syntactic data, functionalize the syntactic information by a key-value memory network (KVMN), and fuse them by attention mechanism. Then the syntactic information and lexical information are integrated by a cross-transformer. Finally, we use an inner regularity perception module to capture the internal regularity of each entity for better entity type prediction. The experimental results show that with F1 scores as the evaluation index, the proposed model obtains 96.51%, 96.81%, and 70.12% accuracy rates on MSRA, resume, and Weibo datasets, respectively.

Linguistic Analysis for Identifying Depression and Subsequent Suicidal Ideation on Weibo: Machine Learning Approaches.

Depression is one of the most common mental illnesses but remains underdiagnosed. Suicide, as a core symptom of depression, urgently needs to be monitored at an early stage, i.e., the suicidal ideation (SI) stage. Depression and subsequent suicidal ideation should be supervised on social media. In this research, we investigated depression and concomitant suicidal ideation by identifying individuals' linguistic characteristics through machine learning approaches. On Weibo, we sampled 487,251 posts from 3196 users from the depression super topic community (DSTC) as the depression group and 357,939 posts from 5167 active users on Weibo as the control group. The results of the logistic regression model showed that the SCLIWC (simplified Chinese version of LIWC) features such as affection, positive emotion, negative emotion, sadness, health, and death significantly predicted depression (Nagelkerke's R2 = 0.64). For model performance: F-measure = 0.78, area under the curve (AUC) = 0.82. The independent samples' t-test showed that SI was significantly different between the depression (0.28 ± 0.5) and control groups (-0.29 ± 0.72) (t = 24.71, p < 0.001). The results of the linear regression model showed that the SCLIWC features, such as social, family, affection, positive emotion, negative emotion, sadness, health, work, achieve, and death, significantly predicted suicidal ideation. The adjusted R2 was 0.42. For model performance, the correlation between the actual SI and predicted SI on the test set was significant (r = 0.65, p < 0.001). The topic modeling results were in accordance with the machine learning results. This study systematically investigated depression and subsequent SI-related linguistic characteristics based on a large-scale Weibo dataset. The findings suggest that analyzing the linguistic characteristics on online depression communities serves as an efficient approach to identify depression and subsequent suicidal ideation, assisting further prevention and intervention.

Social Network Text Sentiment Analysis Method Based on CNN-BiGRU in Big Data Environment

Aiming at the serious colloquialism of social network texts and the sparse semantic features, this article proposes a CNN-BiGRU-based sentiment analysis method for social network texts in the big data environment. First, the dependency syntax tree is introduced to represent the dependency relationship between words to construct the word vector to represent the text. Then, sentiment features with different granularity are extracted by multiple convolution kernels of different sizes in a convolution neural network (CNN). These sentiment features are input into bidirectional gated recurrent unit (BiGRU) network for analysis to obtain deeper sentiment features. Finally, a certain number of neurons are discarded by the Dropout method, and sentiment types are classified by the Sigmoid activation function. The Weibo_senti_100k Weibo data set is used to demonstrate the proposed method. The results show that if the Dropout value is set to 0.25 and the Adam optimizer is selected, the analysis performance is the best. The accuracy, precision, recall, and AUC are about 94.09%, 95.13%, 92.87%, and 0.953, respectively, which has certain application value.

Deep adaptation of CNN in Chinese named entity recognition

AbstractNamed entity recognition (NER) is an important task in the field of natural language processing, but it is more challenging in Chinese because of the lack of natural delimiters. The traditional character‐based Chinese NER model directly uses long short‐term memory (LSTM), gated recurrent units, and other sequence models to extract sentence‐level information from character sequences, resulting in the lack of word‐level information in the model. Therefore, a Chinese NER model called ChineseBERT‐CNNs‐BiLSTM‐CRF was proposed, which uses the ChineseBERT pretrained model as the embedding layer so that the vector representation of each Chinese character contained pinyin, glyph, and conventional character information. In addition, a CNN‐based neural network structure called CNNs was presented to extract word‐level information from character sequences and alleviate the problem of entity boundary recognition. BiLSTM was used to extract global features (i.e., sentence‐level information) and predict the corresponding labels of character sequences. Further, conditional random field (CRF) was employed to impose certain rules on the prediction of BiLSTM to enhance the recognition effect of the model. The experimental results revealed that the F1 values of the model on MSRA, people's Daily, and Weibo datasets reached 95.76, 96.61, and 70.00%, respectively, highlighting the effectiveness of the model.

Multimodal false information detection method based on Text-CNN and SE module.

False information detection can detect false information in social media and reduce its negative impact on society. With the development of multimedia, the multimodal content contained in false information is increasing, so it is important to use multimodal features to detect false information. This paper mainly uses information from two modalities, text and image. The features extracted by the backbone network are not further processed in the previous work, and the problems of noise and information loss in the process of fusing multimodal features are ignored. This paper proposes a false information detection method based on Text-CNN and SE modules. We use Text-CNN to process the text and image features extracted by BERT and Swin-transformer to enhance the quality of the features. In addition, we use the modified SE module to fuse text and image features and reduce the noise in the fusion process. Meanwhile, we draw on the idea of residual networks to reduce information loss in the fusion process by concatenating the original features with the fused features. Our model improves accuracy by 6.5% and 2.0% on the Weibo dataset and Twitter dataset compared to the attention based multimodal factorized bilinear pooling. The comparative experimental results show that the proposed model can improve the accuracy of false information detection. The results of ablation experiments further demonstrate the effectiveness of each module in our model.

SEMI-FND: Stacked ensemble based multimodal inferencing framework for faster fake news detection

Fake News Detection (FND) is an essential field in natural language processing that aims to identify and check the truthfulness of significant claims in a news article to decide the news veracity. FND finds its uses in preventing social, political, and national damage caused due to the misrepresentation of facts that may harm a particular section of society. Further, with the explosive rise in fake news dissemination over social media, including images and text, it has become imperative to identify fake news faster and more accurately. This work investigates a novel multimodal stacked ensemble-based framework (SEMI-FND) for fake news detection. Focus is also kept on ensuring faster performance with fewer parameters. A deep unimodal analysis is done on the image modality to identify NasNet Mobile as the most appropriate model to improve multimodal performance further. For text, an ensemble of BERT and ELECTRA has been used. The approach was evaluated on Twitter MediaEval Dataset and Weibo Corpus. The suggested framework offered 85.80% and 86.83% accuracy on the Twitter and Weibo datasets. These reported metrics are superior when compared to similar recent works. This work also reports a reduction in training parameters compared to its potential counterparts. The developed framework offered an overall parameter reduction of at least 20% with a 2% and 60% reduction on the image and text modality, respectively. Therefore, based on the investigations presented, it is concluded that applying a stacked ensembling significantly improves FND over other approaches while also improving speed.

Weibo Depression Posts Detection by Natural Language Processing

The goal of this paper is to detect depression based on the posts on social media. The dataset combined both tweet dataset and Weibo dataset scraped from the social media. To classify emotions, researchers have been using traditional models such as Bagging, Support Vector Machines, Decision tree, Multinomial Naïve Bayesian and K-nearest neighbor. In this paper, K- nearest neighbor is chosen based on the better precision in result. The main challenge is Chinese context translation and complexity of the context of the post. Finally, an UI page is designed to complete the mission to input a Weibo ID and output of the depression classification. Our approach achieves relatively higher quality results compared to the previous models in literature, while combining depression detection with the real-time social media posts. With this system, we demonstrate the practicability of our project by predicting the depression situation of Internet users through the model, to bring help to the depressed people or people with potential depression tendencies in society.

User Behavior Prediction Based on DCGAN: The Case of Sina Weibo

&lt;p&gt;E-commerce marketing forces are taking advantage of microblogs to deliver their advertisements to promote product information. The success of product information diffusion in microblog depends greatly on user behaviors -- browsing, commenting and reposting. In this paper, we divide user behaviors of Sina Weibo into four types corresponding to four different colors, and propose a method to predict user behavior based on DCGAN (Deep Convolutional Generative Adversarial Nets). By analyzing a real Sina Weibo dataset, the experimental results show that the prediction accuracy of the four types of user behaviors reaches more than 80%, which proves that our method is feasible and effective, and also can help companies succeed in their product advertisements.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

Group behavior dissemination model of social hotspots based on data enhancement and data representation

The emergence and dissemination of hotspots in social networks mainly depend on the participation of group users. In this paper, considering the sparsity and complexity of effective data, we propose a group behavior dissemination model on the basis of data enhancement and data representation. First, given the inaccurate prediction results caused by the sparsity of valid data and the advantages of Generative Adversarial Networks (GAN) in learning data distribution and enhancing data, GAN is introduced to generate homomorphic data. We found that the accuracy improved by at least 6%. Second, with the diversity and complexity of the hotspot feature space and the ability of representation learning to mine hidden features of the hotspot, we designed a new method, called HP2vec, convert the feature space to a low rank and dense vector. Finally, considering the dynamic time limit of hotspot spreading, we create time slices to discretize the life of a hotspot and propose a dynamic dissemination method based on CNN. The experimental section shows that the accuracy of this method is as high as 86% in Weibo dataset and as high as 93% in twitter dataset. The model alleviates data sparseness and effectively predicts the group behavior in hotspots.