scholarly journals MANIN: Multi-Attention Neural Interaction Networks for Social Rumor Detection

2021 ◽  
Author(s):  
Sun Jiehu ◽  
Wu Yue
Keyword(s):  
Social Networks ◽  
Semantic Information ◽  
Interaction Network ◽  
Detection Methods ◽  
Accuracy Rate ◽  
User Interactions ◽  
Neural Interaction ◽  
Public Networks ◽  
Rumor Detection ◽  
Textual Content

Abstract With the fast-changing development of emerging online media, it has be-come apparent that information on social networks is characterized by extensive, fast and timely spreading. The absence of effective detection methods and moni-toring means has led to a massive outbreak of rumors. Therefore, accurate detection and timely suppression of rumors in social networks is a vital task in maintaining social security and purifying public networks. Most existing work relies only on monotonous textual content and shallow semantic information, and lacks critical at-tention to and potential mining of user relationships. Such being the case, we can better improve these problems by employing attention mechanisms. In this paper, we proposea Multi-Attention Neural Interaction Network (MANIN) for rumor detection, which consists mainly of a self-attention-based BERT encoder, a post-comment co-attention mechanism, and a graph attention neural network for mining potential user interactions. We have conducted numerous experiments on real datasets and verified their validity, and the results show that the model proposed by us outperforms existing models with an accuracy rate of 81.6%.

scholarly journals COVID-19 Rumor Detection on Social Networks Based on Content Information and User Response

2021 ◽  
Vol 9 ◽  
Author(s):  
Jianliang Yang ◽  
Yuchen Pan
Keyword(s):  
Social Networks ◽  
Deep Learning ◽  
Detection Method ◽  
Detection Methods ◽  
Time Constraints ◽  
Human Society ◽  
Limited Time ◽  
Response Information ◽  
Rumor Detection ◽  
Content Information

The outbreak of COVID-19 has caused a huge shock for human society. As people experience the attack of the COVID-19 virus, they also are experiencing an information epidemic at the same time. Rumors about COVID-19 have caused severe panic and anxiety. Misinformation has even undermined epidemic prevention to some extent and exacerbated the epidemic. Social networks have allowed COVID-19 rumors to spread unchecked. Removing rumors could protect people’s health by reducing people’s anxiety and wrong behavior caused by the misinformation. Therefore, it is necessary to research COVID-19 rumor detection on social networks. Due to the development of deep learning, existing studies have proposed rumor detection methods from different perspectives. However, not all of these approaches could address COVID-19 rumor detection. COVID-19 rumors are more severe and profoundly influenced, and there are stricter time constraints on COVID-19 rumor detection. Therefore, this study proposed and verified the rumor detection method based on the content and user responses in limited time CR-LSTM-BE. The experimental results show that the performance of our approach is significantly improved compared with the existing baseline methods. User response information can effectively enhance COVID-19 rumor detection.

scholarly journals Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph

Symmetry ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 1806
Author(s):  
Zunwang Ke ◽  
Zhe Li ◽  
Chenzhi Zhou ◽  
Jiabao Sheng ◽  
Wushour Silamu ◽  
...  
Keyword(s):  
Social Media ◽  
Domain Knowledge ◽  
Semantic Information ◽  
Semantic Representation ◽  
Detection Methods ◽  
Ablation Study ◽  
Rumor Detection ◽  
Organic Combination ◽  
Global And Local ◽  
Share Information

Social media had a revolutionary impact because it provides an ideal platform for share information; however, it also leads to the publication and spreading of rumors. Existing rumor detection methods have relied on finding cues from only user-generated content, user profiles, or the structures of wide propagation. However, the previous works have ignored the organic combination of wide dispersion structures in rumor detection and text semantics. To this end, we propose KZWANG, a framework for rumor detection that provides sufficient domain knowledge to classify rumors accurately, and semantic information and a propagation heterogeneous graph are symmetry fused together. We utilize an attention mechanism to learn a semantic representation of text and introduce a GCN to capture the global and local relationships among all the source microblogs, reposts, and users. An organic combination of text semantics and propagating heterogeneous graphs is then used to train a rumor detection classifier. Experiments on Sina Weibo, Twitter15, and Twitter16 rumor detection datasets demonstrate the proposed model’s superiority over baseline methods. We also conduct an ablation study to understand the relative contributions of the various aspects of the method we proposed.

scholarly journals A Multifeature Complementary Attention Mechanism for Image Topic Representation in Social Networks

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Lei Shi ◽  
Jia Luo ◽  
Gang Cheng ◽  
Xia Liu ◽  
Gang Xie
Keyword(s):  
Social Networks ◽  
Semantic Information ◽  
Image Data ◽  
Image Features ◽  
Attention Mechanism ◽  
Detection Methods ◽  
Sina Weibo ◽  
Evaluation Measures ◽  
Optimal Accuracy ◽  
Object Features

Image topic representation in social networks is vital for people to get significant and valuable content. However, this task is difficult and challenging due to the complexity of image features. This paper proposes a multifeature complementary attention mechanism for image topic representation named CATR. CATR uses scene-level and instance-level object detection methods to obtain the object information on social networks. Here, the image features are divided into focused features and unfocused features. Focused features are used to learn and express semantic information, while unfocused features are used to filter out noise information in focused feature extraction. The attention mechanism is constructed by combining the object features and the features of the image itself, while the image topic representation in social networks is realized by the complementary attention mechanism. Based on the real image data of Sina Weibo and Mir-Flickr 25K, several groups of comparative experiments are constructed to verify the performance of the proposed CATR by leveraging different evaluation measures. The experimental results demonstrate that the proposed CATR obtains an optimal accuracy and significantly outperforms the other comparison methods in image topic representation.

Analysis of User Interactions in Online Social Networks

2011 ◽  
Author(s):  
Seokchan Yun ◽  
Heungseok Do ◽  
Jinuk Jung ◽  
Song Mina ◽  
Namgoong Hyun ◽  
...  
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
User Interactions

Applications of random graphs

2017 ◽  
Author(s):  
A.C.C. Coolen ◽  
A. Annibale ◽  
E.S. Roberts
Keyword(s):  
Social Networks ◽  
Random Graphs ◽  
Interaction Network ◽  
Power Grids ◽  
Protein Protein Interaction ◽  
Topological Features ◽  
First Case ◽  
The Stability ◽  
Protein Protein Interaction Network

This chapter reviews graph generation techniques in the context of applications. The first case study is power grids, where proposed strategies to prevent blackouts have been tested on tailored random graphs. The second case study is in social networks. Applications of random graphs to social networks are extremely wide ranging – the particular aspect looked at here is modelling the spread of disease on a social network – and how a particular construction based on projecting from a bipartite graph successfully captures some of the clustering observed in real social networks. The third case study is on null models of food webs, discussing the specific constraints relevant to this application, and the topological features which may contribute to the stability of an ecosystem. The final case study is taken from molecular biology, discussing the importance of unbiased graph sampling when considering if motifs are over-represented in a protein–protein interaction network.

Limitation of degree information for analyzing the interaction evolution in online social networks

2014 ◽  
Vol 25 (10) ◽  
pp. 1450056 ◽  
Author(s):  
Ke-Ke Shang ◽  
Wei-Sheng Yan ◽  
Xiao-Ke Xu
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Social Services ◽  
Online Social Networks ◽  
Dynamic Network ◽  
Interaction Network ◽  
Strength Distribution ◽  
Customer Churn ◽  
Dynamic Social Network ◽  
Temporal Interactions

Previously many studies on online social networks simply analyze the static topology in which the friend relationship once established, then the links and nodes will not disappear, but this kind of static topology may not accurately reflect temporal interactions on online social services. In this study, we define four types of users and interactions in the interaction (dynamic) network. We found that active, disappeared, new and super nodes (users) have obviously different strength distribution properties and this result also can be revealed by the degree characteristics of the unweighted interaction and friendship (static) networks. However, the active, disappeared, new and super links (interactions) only can be reflected by the strength distribution in the weighted interaction network. This result indicates the limitation of the static topology data on analyzing social network evolutions. In addition, our study uncovers the approximately stable statistics for the dynamic social network in which there are a large variation for users and interaction intensity. Our findings not only verify the correctness of our definitions, but also helped to study the customer churn and evaluate the commercial value of valuable customers in online social networks.

Characterization of Fake News Based on Subjectivity Lexicons

2020 ◽  
Vol 1 (4) ◽  
pp. 419-441
Author(s):  
Caio L.M. Jeronimo ◽  
Leandro B. Marinho ◽  
Cclaudio E.C. Carmpelo ◽  
Adriano Veloso ◽  
Allan S. Da Costa Melo
Keyword(s):  
Social Networks ◽  
Brazilian Portuguese ◽  
News Article ◽  
Bag Of Words ◽  
Fake News ◽  
Feature Vectors ◽  
Textual Content

While many works investigate spread patterns of fake news in social networks, we focus on the textual content. Instead of relying on syntactic representations of documents (aka Bag of Words) as many works do, we seek more robust representations that may better differentiate fake from legitimate news. We propose to consider the subjectivity of news under the assumption that the subjectivity levels of legitimate and fake news are significantly different. For computing the subjectivity level of news, we rely on a set subjectivity lexicons for both Brazilian Portuguese and English languages. We then build subjectivity feature vectors for each news article by calculating the Word Mover's Distance (WMD) between the news and these lexicons considering the embedding the news words lie in, in order to analyze and classify the documents. The results demonstrate that our method is robust, especially in scenarios where training and test domains are different.

scholarly journals ConAnomaly: Content-Based Anomaly Detection for System Logs

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6125
Author(s):  
Dan Lv ◽  
Nurbol Luktarhan ◽  
Yiyong Chen
Keyword(s):  
Anomaly Detection ◽  
Semantic Information ◽  
Short Term Memory ◽  
Weighted Average ◽  
Detection Methods ◽  
Detection Model ◽  
Part Of Speech Tagging ◽  
Part Of Speech ◽  
System Logs ◽  
System Maintenance

Enterprise systems typically produce a large number of logs to record runtime states and important events. Log anomaly detection is efficient for business management and system maintenance. Most existing log-based anomaly detection methods use log parser to get log event indexes or event templates and then utilize machine learning methods to detect anomalies. However, these methods cannot handle unknown log types and do not take advantage of the log semantic information. In this article, we propose ConAnomaly, a log-based anomaly detection model composed of a log sequence encoder (log2vec) and multi-layer Long Short Term Memory Network (LSTM). We designed log2vec based on the Word2vec model, which first vectorized the words in the log content, then deleted the invalid words through part of speech tagging, and finally obtained the sequence vector by the weighted average method. In this way, ConAnomaly not only captures semantic information in the log but also leverages log sequential relationships. We evaluate our proposed approach on two log datasets. Our experimental results show that ConAnomaly has good stability and can deal with unseen log types to a certain extent, and it provides better performance than most log-based anomaly detection methods.

scholarly journals A Study of Rumor Detection based on Social Network Topic Models Relationship

2020 ◽  
Author(s):  
Diogo Nolasco ◽  
Jonice Oliveira
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Local Community ◽  
Topic Model ◽  
Fake News ◽  
Detection Problem ◽  
Model Method ◽  
Show Evidence ◽  
Rumor Detection ◽  
Scientific Topic

The rumor detection problem on social networks has attracted considerable attention in recent years with the rise of concerns about fake news and disinformation. Most previous works focused on detecting rumors by individual messages, classifying whether a post or blog entry is considered a rumor or not. This paper proposes a method for rumor detection on topic-level that identifies whether a social topic related to a scientific topic is a rumor. We propose the use of a topic model method on social and scientific domains and correlate the topics found to detect the most prone to be rumors. Results applied in the Zika epidemic scenario show evidence that the least correlated topics contain a mix of rumors and local community discussions.

Sign in / Sign up

Export Citation Format

Share Document