Search

Online Social Networks (OSNs) have been used as the means for a variety of applications. For example, social networking platform has been used in employment system, e-Commerce and CRM system to improve the quality of recommendations with the assistance of social networks. In these applications, social influence acts as a significant role, affecting people's decision-making. However, the existing social influence evaluation methods do not fully consider the social contexts, i.e., the social relationships and the social trust between participants, and the preferences of participants, which have significant impact on social influence evaluation in OSNs. Thus, these existing methods cannot deliver accurate social influence evaluation results. In our paper, we propose a Trust-Oriented Social Influence evaluation method, called TOSI , with taking the social contexts into account. We conduct experiments onto two real social network datasets, i.e., Epinions and DBLP . The experimental results illustrate that our TOSI method greatly outperforms the state-of-the-art method SoCap in terms of effectiveness, efficiency and robustness. [ABSTRACT FROM AUTHOR]

• We design a multi-dimensional information integrated graph neural network, which integrates the category and time information into the graph embedding process, so as to obtain more fine-grained item representations. • Considering the lack of time sensitivity for the traditional self-attention mechanism, we integrate interaction time information into the self-attention mechanism, so as to capture the user's dynamic preferences more accurately. • We conduct extensive experiments on three real-world datasets. Our experiment results demonstrate the superior performance of our proposed method comparing with other state-of-the-art baselines. Graph neural networks (GNNs) technology has been widely used in recommendation systems because most information in recommendation systems has a graph structure in nature, and GNNs have advantages in graph representation learning. In sequential recommendation, the relationships between interacting items can be constructed as an isomorphic graph, and (GNNs) can capture high-order information between graph nodes. Many models have used graph-based methods for sequential recommendation, and achieved great success. However, the existing research only considers the number of interactions between items when constructing the item graph. As such, revisions are needed to capture the multi-dimensional transformation relationships between items. Hence, we emphasize the importance of multi-dimensional information, and we propose a C ategory and T ime information integrated G raph N eural N etwork (CTGNN), which combines the item category and interaction time information with a multi-layer graph convolution network to form multi-dimensional fine-grained item representations. In addition, we design a temporal self-attention network to model the dynamic user preference and make the next-item recommendation. Finally, we conduct extensive experiments on three real-world datasets, and the results demonstrate the excellent performance of the proposed model. [ABSTRACT FROM AUTHOR]

Data repairing aims at discovering and correcting erroneous data in databases. In this paper, we develop Web-ADARE, an end-to-end web-aided data repairing system, to provide a feasible way to involve the vast data sources on the Web in data repairing. Our main attention in developing Web-ADARE is paid on the interaction problem between web-aided repairing and rule-based repairing, in order to minimize the Web consultation cost while reaching predefined quality requirements. The same interaction problem also exists in crowd-based methods but this is not yet formally defined and addressed. We first prove in theory that the optimal interaction scheme is not feasible to be achieved, and then propose an algorithm to identify a scheme for efficient interaction by investigating the inconsistencies and the dependencies between values in the repairing process. Extensive experiments on three data collections demonstrate the high repairing precision and recall of Web-ADARE, and the efficiency of the generated interaction scheme over several baseline ones. [ABSTRACT FROM AUTHOR]

Accurate and fast short-term traffic flow prediction plays a vital role in the construction of future smart cities. To address large bandwidth consumption and high delay in traditional cloud solutions, and improve the accuracy and timeliness of traffic prediction, this paper introduces a novel three-layer Cloud-Edge-IoT traffic flow edge computing architecture, and proposes a short-term Traffic Flow Prediction Method based on Spatial–Temporal Correlation (TFPM-STC), in which Principal Component Analysis (PCA) is adopted for analyzing the intersection correlation, and the Convolution-Gated Recurrent Unit (Conv-GRU) and Bidirectional GRU (Bi-GRU) are used for extracting the spatial–temporal and periodic features of the traffic flow. Experiment results show that compared with existing methods, the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of TFPM-STC are reduced by about 16.5 points on average, and there is a significant reduction in training time and prediction time. • A novel traffic flow edge computing architecture is proposed. • A traffic flow prediction method based on spatial–temporal correlation is proposed. • Using principal component analysis method saves training time and prediction time. • Extracting spatial–temporal and periodic feature improves the accuracy of prediction. [ABSTRACT FROM AUTHOR]