The fast spreading of fake news stories on social media can cause inestimable social harm. Developing effective methods to detect them early is of paramount importance. A major challenge of fake news early detection is fully utilizing the limited data observed at the early stage of news propagation and then learning useful patterns from it for identifying fake news. In this article, we propose a novel deep neural network to detect fake news early. It has three novel components: (1) a status-sensitive crowd response feature extractor that extracts both text features and user features from combinations of users’ text response and their corresponding user profiles, (2) a position-aware attention mechanism that highlights important user responses at specific ranking positions, and (3) a multi-region mean-pooling mechanism to perform feature aggregation based on multiple window sizes. Experimental results on two real-world datasets demonstrate that our proposed model can detect fake news with greater than 90% accuracy within 5 minutes after it starts to spread and before it is retweeted 50 times, which is significantly faster than state-of-the-art baselines. Most importantly, our approach requires only 10% labeled fake news samples to achieve this effectiveness under PU-Learning settings.

In the midst of today's pervasive influence of social media, automatically detecting fake news is drawing significant attention from both the academic communities and the general public. Existing detection approaches rely on machine learning algorithms with a variety of news characteristics to detect fake news. However, such approaches have a major limitation on detecting fake news early, i.e., the information required for detecting fake news is often unavailable or inadequate at the early stage of news propagation. As a result, the accuracy of early detection of fake news is low. To address this limitation, in this paper, we propose a novel model for early detection of fake news on social media through classifying news propagation paths. We first model the propagation path of each news story as a multivariate time series in which each tuple is a numerical vector representing characteristics of a user who engaged in spreading the news. Then, we build a time series classifier that incorporates both recurrent and convolutional networks which capture the global and local variations of user characteristics along the propagation path respectively, to detect fake news. Experimental results on three real-world datasets demonstrate that our proposed model can detect fake news with accuracy 85% and 92% on Twitter and Sina Weibo respectively in 5 minutes after it starts to spread, which is significantly faster than state-of-the-art baselines.

With the rapid development of the Internet and its applications, growing volumes of documents increasingly become interconnected to form large‐scale document networks. Accordingly, topic modeling in a network of documents has been attracting continuous research attention. Most of the existing network‐based topic models assume that topics in a document are influenced by its directly linked neighbouring documents in a document network and overlook the potential influence from indirectly linked ones. The existing work also has not carefully modeled variations of such influence among neighboring documents. Recognizing these modeling limitations, this paper introduces a novel Local Context‐Aware LDA Model (LC‐LDA), which is capable of observing a local context comprising a rich collection of documents that may directly or indirectly influence the topic distributions of a target document. The proposed model can also differentiate the respective influence of each document in the local context on the target document according to both structural and temporal relationships between the two documents. The proposed model is extensively evaluated through multiple document clustering and classification tasks conducted over several large‐scale document sets. Evaluation results clearly and consistently demonstrate the effectiveness and superiority of the new model with respect to several state‐of‐the‐art peer models.

In the midst of today's pervasive influence of social media content and activities, information credibility has increasingly become a major issue. Accordingly, identifying false information, e.g., rumors circulated in social media environments, attracts expanding research attention and growing interests. Many previous studies have exploited user-independent features for rumor detection. These prior investigations uniformly treat all users relevant to the propagation of a social media message as instances of a generic entity. Such a modeling approach usually adopts a homogeneous network to represent all users, the practice of which ignores the variety across an entire user population in a social media environment. Recognizing this limitation in modeling methodologies, this paper explores user-specific features in a social media environment for rumor detection. The new approach hypothesizes whether a user tending to spread a rumor message is dependent on specific attributes of the user in addition to content characteristics of the message itself. Under this hypothesis, the information propagation patterns of rumors versus those of credible messages in a social media environment are differentiable. To explore and exploit this hypothesis, we develop a new information propagation model based on a heterogeneous user representation and modeling approach. By applying the new approach, we are able to differentiate rumors from credible messages through observing distinctions in their respective propagation patterns in social media. The experimental results show that the new information propagation model based on heterogeneous user representation can effectively distinguish rumors from credible social media content. Our experimental findings further show that rumors are more likely to spread among certain user groups.

With the rapid development of Web 2.0 and the Internet of things, predicting relationships in heterogeneous networks has evolved as a heated research topic. Traditionally, people analyze existing relationships in heterogeneous networks that relate in a particular way to a target relationship of interest to predict the emergence of the target relationship. However most existing methods are incapable of systematically identifying relevant relationships useful for the prediction task, especially those relationships involving multiple objects of heterogeneous types, which may not rest on a simple path in the concerned heterogeneous network. Another problem with the current practice is that the existing solutions often ignore the dynamic evolution of the network structure after the introduction of newly emerged relationships. To overcome the first limitation, we propose a new algorithm that can systematically and comprehensively detect relevant relationships useful for the prediction of an arbitrarily given target relationship through a disciplined graph searching process. To address the second limitation, the new algorithm leverages a series of temporally-sensitive features for the relationship occurrence prediction via a supervised learning approach. To explore the effectiveness of the new algorithm, we apply the prototype implementation of the algorithm on the DBLP bibliographic network to predict the author citation relationships and compare the algorithm performance with that of a state-of-the-art peer method and a series of baseline methods. The comparison shows consistently higher prediction accuracy under a range of prediction scenarios.