Identifying fake news on media has been an important issue. This is especially true considering the wide spread of rumors on popular social networks such as Twitter. Various kinds of techniques have been proposed for automatic rumor detection. In this work, we study the application of graph neural networks for rumor classification at a lower level, instead of applying existing neural network architectures to detect rumors. The responses to true rumors and false rumors display distinct characteristics. This suggests that it is essential to capture such interactions in an effective manner for a deep learning network to achieve better rumor detection performance. To this end we present a simplified aggregation graph neural network architecture. Experiments on publicly available Twitter datasets demonstrate that the proposed network has performance on a par with or even better than that of state-of-the-art graph convolutional networks, while significantly reducing the computational complexity.

Entity attribute extraction, which converts chaotic text data to structured knowledge, plays an important role in natural language processing (NLP). Many previous studies proved that the representation of text has a significant impact on the results of attribute extraction. In this paper, we propose a novel model to obtain the discriminative representation of sentences by applying the Siamese architecture. Specifically, we simultaneously input two variable-length sentences in the training stage of our model, namely, the main sentence and its similar or dissimilar partner. This scheme of pair is beneficial for entity attribute extraction. First, the entity attribute extraction community suffers the insufficient but expensive labeled data, the two input sets produce much more samples for the representation learning and can be treated as a useful data augmentation method. More importantly, the co-learning by the Siamese architecture achieves more interesting embedding than the separate way, since the informative relation between the focused sentence and its partner help the representation learning to explore more essential semantics and keep stable to the variation of wording and syntax of a sentence. The experiments on the Wikipedia data show that our model takes advantage of the Siamese architecture for sentence embedding and achieves significant improvements on attribute extraction as compared with baselines. To the best of our knowledge, we are the first to introduce the Siamese network into the person entity attribute extraction, which we proved to achieve the state of the art.

The recent development of the mobile Internet and the rise of social media have significantly enriched the way people access information. Accurate modeling of the probability of information propagation between users is essential for studying information dissemination issues in social networks. As the dissemination of information is inseparable from the interactions between users, the probability of propagation can be characterized by such interactions. In general, there are differences in the dissemination modes of information that carry different topics in a real social network. Using these factors, we propose a method (TMIVM) to measure the mutual influence between users at the topic level. The method associates two vectorization parameters for each user—an influence vector and a susceptibility vector—where the dimensions of the vector represent different topic categories. The magnitude of the mutual influence between users on different topics can be obtained by the product of the corresponding elements of the vectors. Specifically, in this article, we fit a social network historical information cascade data through Survival Analysis to learn the parameters of the influence and susceptibility vectors. The experimental results on a synthetic data set and a real Microblog data set show that this method better measures the propagation probability and information cascade predictions compared to other methods.