The rapid growth of social networks has enabled the widespread deployment of social bots that manipulate public opinion and disseminate misinformation, thereby posing significant cybersecurity risks. Most existing detection methods for social bots primarily focus on individual features and low-order neighbor information, while neglecting the higher-order topological semantics embedded in frequent substructures, or motifs. This oversight limits their ability to effectively identify sophisticated social bots exhibiting complex behaviors. To address this gap, we propose a novel approach called the multi-motif attention fusion network (MMAFN). Our method enhances the ability to capture complex structures by explicitly modeling higher-order topological relationships within social graphs. Specifically, we first extract typical network motifs from the original graph to generate motif networks that preserve higher-order interaction patterns. We then integrate the original graph structure with these motif networks across multiple scales, constructing a composite adjacency relationship that captures multilevel semantics. Following this integration, we design specialized graph convolution operators that perform parallel feature propagation based on the composite adjacency matrix, generating node representations that incorporate multiorder topological information. Finally, we dynamically merge features from different motif views through an attention mechanism, establishing interaction channels between motifs and ultimately predicting the anomaly probability of user accounts. Experimental results on two large-scale datasets demonstrate that our method significantly outperforms state-of-the-art methods, exhibiting superior detection performance and robust generalization capabilities.

The identification of influential nodes in multilayer networks is a rapidly growing area in network science. However, insufficient consideration of both inter- and intra-layer weights in existing research has limited the effectiveness of node identification methods. To address this gap, we propose a novel algorithm, coupling weighted intra-layer and inter-layer influence factors (CWIIIF), which accurately identifies nodes that exert significant influence in multilayer networks. The algorithm integrates weighted intra- and inter-layer influence factors, taking into account the unique properties of multilayer network structures. First, we define a set of layer weight influence parameters, including active nodes, active paths, and communication intersections between layers, to determine the weight of each network layer. We then calculate the intra-layer influence of each node using a combination of K-shell and betweenness centrality methods. Finally, we introduce a set of coupled equations that convert the intra-layer influence vectors into scalar values by incorporating the weights of each layer, producing a final influence score for each node. To validate the effectiveness of our algorithm, we conducted four comparative experiments across nine real-world and one synthetic multilayer networks. The results demonstrate that our algorithm significantly outperforms nine classical and state-of-the-art methods for identifying influential nodes.

Like other tropical and subtropical regions, influenza viruses can circulate year-round in Hong Kong. However, during the COVID-19 pandemic, there was a significant decrease in influenza activity. The objective of this study was to retrospectively forecast influenza activity during the year 2020 and assess the impact of COVID-19 public health social measures (PHSMs) on influenza activity and hospital admissions in Hong Kong. Using weekly surveillance data on influenza virus activity in Hong Kong from 2010 to 2019, we developed a statistical modeling framework to forecast influenza virus activity and associated hospital admissions. We conducted short-term forecasts (1-4 weeks ahead) and medium-term forecasts (1-13 weeks ahead) for the year 2020, assuming no PHSMs were implemented against COVID-19. We estimated the reduction in transmissibility, peak magnitude, attack rates, and influenza-associated hospitalization rate resulting from these PHSMs. For short-term forecasts, mean ambient ozone concentration and school holidays were found to contribute to better prediction performance, while absolute humidity and ozone concentration improved the accuracy of medium-term forecasts. We observed a maximum reduction of 44.6% (95% CI: 38.6% - 51.9%) in transmissibility, 75.5% (95% CI: 73.0% - 77.6%) in attack rate, 41.5% (95% CI: 13.9% - 55.7%) in peak magnitude, and 63.1% (95% CI: 59.3% - 66.3%) in cumulative influenza-associated hospitalizations during the winter-spring period of the 2019/2020 season in Hong Kong. The implementation of PHSMs to control COVID-19 had a substantial impact on influenza transmission and associated burden in Hong Kong. Incorporating information on factors influencing influenza transmission improved the accuracy of our predictions.

Medication combination prediction (MCP) can provide assistance for experts in the more thorough comprehension of complex mechanisms behind health and disease. Many recent studies focus on the patient representation from the historical medical records, but neglect the value of the medical knowledge, such as the prior knowledge and the medication knowledge. This article develops a medical-knowledge-based graph neural network (MK-GNN) model which incorporates the representation of patients and the medical knowledge into the neural network. More specifically, the features of patients are extracted from their medical records in different feature subspaces. Then these features are concatenated to obtain the feature representation of patients. The prior knowledge, which is calculated according to the mapping relationship between medications and diagnoses, provides heuristic medication features according to the diagnosis results. Such medication features can help the MK-GNN model learn optimal parameters. Moreover, the medication relationship in prescriptions is formulated as a drug network to integrate the medication knowledge into medication representation vectors. The results reveal the superior performance of the MK-GNN model compared with the state-of-the-art baselines on different evaluation metrics. The case study manifests the application potential of the MK-GNN model.

Phages are the functional viruses that infect bacteria and they play important roles in microbial communities and ecosystems. Phage research has attracted great attention due to the wide applications of phage therapy in treating bacterial infection in recent years. Metagenomics sequencing technique can sequence microbial communities directly from an environmental sample. Identifying phage sequences from metagenomic data is a vital step in the downstream of phage analysis. However, the existing methods for phage identification suffer from some limitations in the utilization of the phage feature for prediction, and therefore their prediction performance still need to be improved further. In this article, we propose a novel deep neural network (called MetaPhaPred) for identifying phages from metagenomic data. In MetaPhaPred, we first use a word embedding technique to encode the metagenomic sequences into word vectors, extracting the latent feature vectors of DNA words. Then, we design a deep neural network with a convolutional neural network (CNN) to capture the feature maps in sequences, and with a bi-directional long short-term memory network (Bi-LSTM) to capture the long-term dependencies between features from both forward and backward directions. The feature map consists of a set of feature patterns, each of which is the weighted feature extracted by a convolution filter with convolution kernels in the CNN slide along the input feature vectors. Next, an attention mechanism is used to enhance contributions of important features. Experimental results on both simulated and real metagenomic data with different lengths demonstrate the superiority of the proposed MetaPhaPred over the state-of-the-art methods in identifying phage sequences.

For better monitoring and controlling influenza, WHO has launched FluNet (recently integrated to FluMART) to provide a unified platform for participating countries to routinely collect influenza-related syndromic, epidemiological and virological data. However, the reported data were incomplete.We propose a novel surveillance system based on data from multiple sources to accurately assess the epidemic status of different countries, especially for those with missing surveillance data in some periods. The proposed method can automatically select a small set of reliable and informative indicators for assessing the underlying epidemic status and proper supporting data to train the predictive model. Our proactive selection method outperforms three other out-of-box methods (linear regression, multilayer perceptron, and long-short term memory) to make accurate predictions.

Text classification is the most fundamental and classical task in the natural language processing (NLP). Recently, graph neural network (GNN) methods, especially the graph-based model, have been applied for solving this issue because of their superior capacity of capturing the global co-occurrence information. However, some existing GNN-based methods adopt a corpus-level graph structure which causes a high memory consumption. In addition, these methods have not taken account of the global co-occurrence information and local semantic information at the same time. To address these problems, we propose a new GNN-based model, namely two windows text gnn model (TW-TGNN), for text classification. More specifically, we build text-level graph for each text with a local sliding window and a dynamic global window. For one thing, the local window sliding inside the text will acquire enough local semantic features. For another, the dynamic global window sliding betweent texts can generate dynamic shared weight matrix, which overcomes the limitation of the fixed corpus level co-occurrence and provides richer dynamic global information. Our experimental results on four benchmark datasets illustrate the improvement of the proposed method over state-of-the-art text classification methods. Moreover, we find that our method captures adequate global information for the short text which is beneficial for overcoming the insufficient contextual information in the process of the short text classification.

Precision mitigation of COVID-19 is in pressing need for postpandemic time with the absence of pharmaceutical interventions. In this study, the effectiveness and cost of digital contact tracing (DCT) technology-based on-campus mitigation strategy are studied through epidemic simulations using high-resolution empirical contact networks of teachers and students. Compared with traditional class, grade, and school closure strategies, the DCT-based strategy offers a practical yet much more efficient way of mitigating COVID-19 spreading in the crowded campus. Specifically, the strategy based on DCT can achieve the same level of disease control as rigid school suspensions but with significantly fewer students quarantined. We further explore the necessary conditions to ensure the effectiveness of DCT-based strategy and auxiliary strategies to enhance mitigation effectiveness and make the following recommendation: social distancing should be implemented along with DCT, the adoption rate of DCT devices should be assured, and swift virus tests should be carried out to discover asymptomatic infections and stop their subsequent transmissions. We also argue that primary schools have higher disease transmission risks than high schools and, thereby, should be alerted when considering reopenings.

Individual mood is important for physical and emotional well-being, creativity and working memory. However, due to the lack of long-term real tracking daily data in individual level, most current works focus their efforts on population level and short-term small group. An ignored yet important task is to find the sentiment spreading mechanism in individual level from their daily behavior data. This paper studies this task by raising the following fundamental and summarization question, being not sufficiently answered by the literature so far:Given a social network, how the sentiment spread? The current individual-level network spreading models always assume one can infect others only when he/she has been infected. Considering the negative emotion spreading characters in individual level, we loose this assumption, and give an individual negative emotion spreading model. In this paper, we propose a Graph-Coupled Hidden Markov Sentiment Model for modeling the propagation of infectious negative sentiment locally within a social network. Taking the MIT Social Evolution dataset as an example, the experimental results verify the efficacy of our techniques on real-world data.

In this paper, we formulate a generalized optimization problem to meet the profit problem for crowdsourced systems with considering three aspects of connectivity, profit and risk. We also propose a routing algorithm for this special scenario, featured by dynamic mobility and social graph. This algorithm has two parts: social graph extraction and social mobility based routing. The first part extracts each patrician's social graph to get the social knowledge. The second part gives a policy for the decider to assign the passages to the leaving nodes according to their social graph. We applied our algorithm into the realistic traces, and compare it with several existing methods. The result shows the competitive performance of this routing algorithm, both in connectivity, profit and risk.

No abstract available.