Rumor Identification Research Articles

A Neuro-Fuzzy Approach to Detect Rumors in Online Social Networks

Along with true information, rumors spread in online social networks (OSN) on an unprecedented scale. In recent days, rumor identification gains more interest among the researchers. Finding rumors also poses other critical challenges like noisy and imprecise input data, data sparsity, and unclear interpretations of the output. To address these issues, we propose a neuro-fuzzy classification approach called the neuro-fuzzy rumor detector (NFRD) to automatically identify the rumors in OSNs. NFRD quickly transforms the input to fuzzy rules which classify the rumor. Neural networks handle larger input data. Fuzzy systems are better in handling uncertainty and imprecision in input data by producing fuzzy rules that effectively eliminate the unclear inputs. NFRD also considers the semantic aspects of information to ensure better classification. The neuro-fuzzy approach addresses the most common problems such as uncertainty elimination, noise reduction, and quicker generalization. Experimental results show the proposed approach performs well against state-of-the-art rumor detecting techniques.

A Parallel Neural Network Approach for Faster Rumor Identification in Online Social Networks

The unprecedented scale of rumor propagation in online social networks urges the necessity of faster rumor identification and control. The identification of rumors in the inception itself is imperative to bring down the harm it could cause to the society at large. But, the available information regarding rumors in inception stages is minimal. To identify rumors with data sparsity, we have proposed a twofold convolutional neural network approach with a new activation function which generalizes faster with higher accuracy. The proposed approach utilizes prominent features such as temporal and content for the classification. This rumor detection method is compared with the state-of-the-art rumor detection approaches and results prove the proposed method identifies rumor earlier than other approaches. Using this approach, the detected rumors with 88% accuracy and 92% precision for experimental datasets is 5% to 35% better than the existing approaches. This automated approach provides better results for larger and scale-free networks.

Computational Rumor Detection Without Non-Rumor: A One-Class Classification Approach

Rumor spreading in online social networks can inflict serious damages on individual, organizational, and societal levels. This problem has been addressed via computational approach in recent years. The dominant computational technique for the identification of rumors is the binary classification that uses rumor and non-rumor for the training. In this method, the way of annotating training data points determines how each class is defined for the classifier. Unlike rumor samples that often are annotated similarly, non-rumors get their labels arbitrarily based on annotators’ volition. Such an approach leads to unreliable classifiers that cannot distinguish rumor from non-rumor consistently. In this paper, we tackle this problem via a novel classification approach called one-class classification (OCC). In this approach, the classifier is trained with only rumors, which means that we do not need the non-rumor data points at all. For this study, we use two primary Twitter data sets in this field and extract 86 features from each tweet. We then apply seven one-class classifiers from three different paradigms and compare their performance. Our results show that this approach can recognize rumors with a high level of F1-score. This approach may influence the predominant mentality of scholars about computational rumor detection and puts forward a new research path toward dealing with this problem.

Research on the Prevention and Control of the Internet Rumor from the Perspective of the Self-Media

With the rapid development of Internet science and technology, the self-media industry is rising gradually. As an important way of information dissemination, more and more self-media platforms are established and the main body of information communication becomes more complex. The self-media not only brings convenience to people’s life but also brings some negative effects. The self-media has more remarkable characteristics in information dissemination. The birth of self-media makes the network appear more suspicious information that cannot be effectively verified. Internet rumors fly all over the sky, which has caused certain influence on the stability of the society. The prevention and control measures of online rumors from the perspective of self-media are studied in this paper for creating a healthier network environment. Firstly, the concepts of self-media and Internet rumors are briefly summarized. Then, the main characteristics of Internet rumors from the perspective of self-media are analyzed. Finally, the prevention and control measures of online rumors, including strengthening supervision, improving the quality of self-media, and strengthening public identification of rumors, are proposed.

Towards early identification of online rumors based on long short-term memory networks

In the social media environment, rumors are constantly breeding and rapidly spreading, which has become a severe social problem, often leading to serious consequences (e.g., social panic and even chaos). Therefore, how to identify rumors quickly and accurately has become a key prerequisite for taking effective measures to curb the spread of rumors and reduce their influence. However, most existing studies employ machine learning based methods to carry out automatic rumor identification by extracting features of rumor contents, posters, and static spreading processes (e.g., follow-ups, thumb-ups, etc.) or by learning the presentation of forwarding contents. These studies fail to take into account the dynamic differences between the spreaders and diffusion structures of rumors and non-rumors. To fill this gap, this paper proposes Long Short-Term Memory (LSTM) network based models for identifying rumors by capturing the dynamic changes of forwarding contents, spreaders and diffusion structures of the whole (in the afterwards identification mode) or only the beginning part (in the halfway identification mode, i.e., early rumor identification) of the spreading process. Experiments conducted on a rumor and non-rumor dataset from Sina Weibo show that the proposed models perform better than existing baselines.

Rumor Classification Model Based on Deep Convolutional Neural Networks

With the rapid development of mobile Internet and big data technology, the recognition classification and trend prediction of rumors became has important research subject. At present, the traditional methods represented by the hidden markov model and support vector machine (SVM) has many problems, such as low classification accuracy, excessive reliance on long-term historical data and weak system practicability. Based on the new generation of artificial intelligence theory, such as deep learning, this paper proposed a rumor classification model based on deep convolutional neural networks. By training deep convolutional neural network, the classifier was constructed to solve the problem of high accuracy identification and classification of network rumors.

Detection of financial rumors using big data analytics: the case of the Bombay Stock Exchange

ABSTRACTMarket regulators and stock exchanges around the globe need to ensure that investors trade in a fair and efficient manner. The main motive for market surveillance is to make the market more efficient and free from rouge elements. Identification of financial rumors is vital for orderly functioning of the stock market. Social media platforms allow spread of unverified information to a large mass quickly due to their interconnected nature and large number of participating members. Due to the deluge of data over various media channels including social media, manual scanning of financial rumors is inefficient. This necessitates the use of a big data infrastructure for collection, storage, and analysis of financial news related data. In this paper, we introduce a framework for automated detection of financial rumors using big data. Our framework is based on extant research on knowledge-based discovery in databases and detection of fraudulent financial activities. We describe an in-depth descriptive case study of the world’s fastest stock exchange, the Bombay Stock Exchange. Through the case, we highlight the importance of analytics for detection of financial rumors and the importance of the big data infrastructure to carry out such a task. We identify several critical factors that lead to successful identification of financial rumors. We believe the framework can be used by market regulators, stock exchanges, and security research agencies to identify information-based market manipulation using a systematic data-driven approach over a big data infrastructure.

Rumor Identification with Maximum Entropy in MicroNet

The widely used applications of Microblog, WeChat, and other social networking platforms (that we call MicroNet) shorten the period of information dissemination and expand the range of information dissemination, which allows rumors to cause greater harm and have more influence. A hot topic in the information dissemination field is how to identify and block rumors. Based on the maximum entropy model, this paper constructs the recognition mechanism of rumor information in the micronetwork environment. First, based on the information entropy theory, we obtained the characteristics of rumor information using the maximum entropy model. Next, we optimized the original classifier training set and the feature function to divide the information into rumors and nonrumors. Finally, the experimental simulation results show that the rumor identification results using this method are better than the original classifier and other related classification methods.

Rumor Identification in Microblogging Systems Based on Users’ Behavior

Rumor Identification in Microblogging Systems Based on Users’ Behavior

Dynamic 8-state ICSAR rumor propagation model considering official rumor refutation

With the rapid development of information networks, negative impacts of rumor propagation become more serious. Nowadays, knowing the mechanisms of rumor propagation and having an efficient official rumor refutation plan play very important roles in reducing losses and ensuring social safety. In this paper we first develop the dynamic 8-state ICSAR (Ignorance, Information Carrier, Information Spreader, Information Advocate, Removal) rumor propagation model to study the mechanism of rumor propagation. Eight influencing factors including information attraction, objective identification of rumors, subjective identification of people, the degree of trust of information media, spread probability, reinforcement coefficient, block value and expert effects which are related to rumor propagation were analyzed. Next, considering these factors and mechanisms of rumor propagation and refutation, the dynamic 8-state ICSAR rumor propagation model is verified by the SIR epidemic model, computer simulation and actual data. Thirdly, through quantitative sensitivity analysis, the detailed function of each influencing factor was studied and shown in the figure directly. According to these mechanisms, we could understand how to block a rumor in a very efficient way and which methods should be chosen in different situations. The ICSAR model can divide people into 8 states and analyze rumor and anti-rumor dissemination in an accurate way. Furthermore, official rumor refutation is considered in rumor propagation. The models and the results are essential for improving the efficiency of rumor refutation and making emergency plans, which help to reduce the possibility of losses in disasters and rumor propagation.