Search Results (216)

Social networks generate vast amounts of data that can reveal patterns of human behaviour, social attachment, and mental states. This paper explores advanced machine learning techniques to detect and model such patterns, focusing on community structures, influential users, and information diffusion pathways. To address the scale, noise, and heterogeneity of social data, we leverage recent advances in graph theory, natural language processing, and anomaly detection. Our framework combines clustering for community detection, sentiment analysis for emotional state inference, and centrality metrics for influence estimation, while integrating multimodal data—including textual and visual content—for richer behavioural insights. Experimental results demonstrate that the proposed approach effectively extracts actionable knowledge, supporting mental well-being and strengthening digital social ties. Furthermore, we emphasise the role of privacy-preserving methods, such as federated learning, to ensure ethical analysis. These findings lay the groundwork for responsible and effective applications of machine learning in social network analysis. Full article

Forecasting over dynamic graph environments necessitates modeling both long-term temporal dependencies and evolving structural patterns. We propose MaGNet-BN, a modular framework that simultaneously performs probabilistic forecasting and dynamic community detection on temporal graphs. MaGNet-BN integrates Bayesian node embeddings for uncertainty modeling, prototype-guided Louvain clustering for community discovery, Markov-based transition modeling to preserve temporal continuity, and reinforcement-based refinement to improve structural boundary accuracy. Evaluated on real-world datasets in pedestrian mobility, energy consumption, and retail demand, our model achieves on average 11.48% lower MSE, 6.62% lower NLL, and 10.82% higher Modularity (Q) compared with the best-performing baselines, with peak improvements reaching 12.0% in MSE, 7.9% in NLL, and 16.0% in Q on individual datasets. It also improves uncertainty calibration (PICP) and temporal community coherence (tARI). Ablation studies highlight the complementary strengths of each component. Overall, MaGNet-BN delivers a structure-aware and uncertainty-calibrated forecasting system that models both temporal evolution and dynamic community formation, with a modular design enabling interpretable predictions and scalable applications across smart cities, energy systems, and personalized services. Full article

This study explores graph-based methods to model and analyze the semantic interplay between editorial taxonomies and user-generated folksonomies on the PornHub platform, using a dataset of over 97,000 videos (2015–2024). We construct and examine a graph of user-assigned tags and platform-defined categories, applying the Leiden community detection algorithm to uncover latent semantic groupings. To enrich the graph structure, we embed textual metadata using state-of-the-art language models (Qwen3-Embedding-4B and all-MiniLM-L6-v2), enabling the integration of natural language processing within graph-based learning. Our analysis reveals that folksonomies partially align with taxonomies through synonymous structures but also diverge by capturing nuanced attributes such as body features and aesthetic styles. These asymmetries highlight how folksonomies introduce higher-resolution semantic layers absent from fixed-category systems. By fusing graph mining, NLP-driven embeddings, and network-based clustering, this work contributes a hybrid methodology for semantic knowledge extraction in large-scale, user-generated content. It offers implications for graph-based recommendation, content moderation, and metadata enrichment—demonstrating the utility of graph-centric AI techniques in real-world multimedia data settings. Full article

Traditional GCN based methods capture the propagation structure between posts, but do not fully model dynamic semantic information, such as the role of specific users on the propagation path and the context of post content that changes over time, leading to a decrease in the accuracy of rumor detection. Therefore, we propose an innovative path attention graph convolution network (PAGCN) framework, which effectively solves this limitation by integrating propagation structure and semantic representation learning. PAGCN first uses the graph neural network (GNN) to model the information transmission path, focusing on the differences between rumor and fact information in communication behavior, such as the differences between depth first and breadth first dissemination modes. Then, in order to enhance the ability of semantic understanding, we design a multi head attention mechanism based on convolutional neural network (CNN), which extracts deep contextual relationships from text content. Furthermore, by introducing the comparative learning technology, PAGCN can adaptively optimize the representation of structural and semantic features, dynamically focus on the most discriminative features, and significantly improve the sensitivity to subtle patterns in rumor propagation. The experimental verification on three benchmark datasets of twitter15, twitter16, and Weibo, shows that the proposed PAGCN performs best among the 17 comparison models, and the accuracy rates on twitter15 and Weibo datasets are 90.9% and 93.9%, respectively, which confirms the effectiveness of the framework in capturing propagation structure and semantic information at the same time. Full article

Community detection in complex networks plays a pivotal role in modern scientific research, including in social network analysis and protein structure analysis. Traditional community detection methods face challenges in integrating heterogeneous multi-source information, capturing global semantic relationships, and adapting to dynamic network evolution. This paper proposes a novel unsupervised multimodal community detection algorithm (UMM) based on fractal iteration. The core idea is to design a dual-channel encoder that comprehensively considers node semantic features and network topological structures. Initially, node representation vectors are derived from structural information (using feature vectors when available, or singular value decomposition to obtain feature vectors for nodes without attributes). Subsequently, a parameter-free graph convolutional encoder (PFGC) is developed based on fractal iteration principles to extract high-order semantic representations from structural encodings without requiring any training process. Furthermore, a semantic–structural dual-channel encoder (DC-SSE) is designed, which integrates semantic encodings—reduced in dimensionality via UMAP—with structural features extracted by PFGC to obtain the final node embeddings. These embeddings are then clustered using the K-means algorithm to achieve community partitioning. Experimental results demonstrate that the UMM outperforms existing methods on multiple real-world network datasets. Full article

Malware evolution presents growing security threats for resource-constrained Internet of Medical Things (IoMT) devices. Conventional federated learning (FL) often suffers from slow convergence, high communication overhead, and fairness issues in dynamic IoMT environments. In this paper, we propose FedGCL, a secure and efficient FL framework integrating contrastive graph representation learning for enhanced feature discrimination, a Jain-index-based fairness-aware aggregation mechanism, an adaptive synchronization scheduler to optimize communication rounds, and secure aggregation via homomorphic encryption within a Trusted Execution Environment. We evaluate FedGCL on four benchmark malware datasets (Drebin, Malgenome, Kronodroid, and TUANDROMD) using 5 to 15 graph neural network clients over 20 communication rounds. Our experiments demonstrate that FedGCL achieves 96.3% global accuracy within three rounds and converges to 98.9% by round twenty—reducing required training rounds by 45% compared to FedAvg—while incurring only approximately 10% additional computational overhead. By preserving patient data privacy at the edge, FedGCL enhances system resilience without sacrificing model performance. These results indicate FedGCL’s promise as a secure, efficient, and fair federated malware detection solution for IoMT ecosystems. Full article

Sparse code multiple access (SCMA) has been a competitive multiple access candidate for future communication networks due to its superiority in spectrum efficiency and providing massive connectivity. However, cell edge users may suffer from great performance degradations due to signal attenuation. Therefore, a cooperative downlink SCMA system is proposed to improve transmission reliability. To the best of our knowledge, multiuser detection is still an open issue for this cooperative downlink SCMA system. To this end, we propose a joint iterative decoding design of the cooperative downlink SCMA system by using the joint factor graph stemming from direct and relay transmission. The closed form bit-error rate (BER) performance of the cooperative downlink SCMA system is also derived. Simulation results verify that the proposed cooperative downlink SCMA system performs better than the non-cooperative one. Full article

With the rapid evolution of social computing, online sentiments have become valuable information for analyzing the latent structure of social networks. Sentiment leaders in social networks are those who bring in new information, ideas, and innovations, disseminate them to the masses, and thus influence the opinions and sentiment of others. Identifying sentiment leaders can help businesses predict marketing campaigns, adjust marketing strategies, maintain their partnerships, and improve their products’ reputations. However, capturing the complex sentiment dynamics from multi-hop interactions and trust/distrust relationships, as well as identifying leaders within sentiment-aligned communities while maximizing sentiment spread efficiently through both direct and indirect paths, is a significant challenge to be addressed. This paper pioneers a challenging and important problem of sentiment leader identification in social networks. To this end, we propose an original solution framework called “SentiRank” and develop the associated algorithms to identify sentiment leaders. SentiRank contains three key technical steps: (1) constructing a sentiment graph from a social network; (2) detecting sentiment communities; (3) ranking the nodes on the selected sentiment communities to identify sentiment leaders. Extensive experimental results based on the real-world datasets demonstrate that the proposed framework and algorithms outperform the existing algorithms in terms of both one-step sentiment coverage and all-path sentiment coverage. Furthermore, the proposed algorithm performs around 6.5 times better than the random approach in terms of sentiment coverage maximization. Full article

This study investigates the mechanisms underlying the diffusion of risk information about genetically modified organisms (GMOs) on the Chinese social media platform Weibo. Drawing upon social contagion theory, we examine how endogenous and exogenous mechanisms shape users’ information-sharing behaviors. An analysis of 388,722 reposts from 2444 original GMO risk-related texts enabled the construction of a comprehensive sharing network, with computational text-mining techniques employed to detect users’ attitudes toward GMOs. To bridge the gap between descriptive and inferential network analysis, we employ a Shannon entropy-based approach to quantify the uncertainty and concentration of attitudinal differences and similarities among sharing and non-sharing dyads, providing an information-theoretic foundation for understanding positional and differential homophily. The entropy-based analysis reveals that information-sharing ties are characterized by lower entropy in attitude differences, indicating greater attitudinal alignment among sharing users, especially among GMO opponents. Building on these findings, the Exponential Random Graph Model (ERGM) further demonstrates that both endogenous network mechanisms (reciprocity, preferential attachment, and triadic closure) and positional homophily influence GMO risk information sharing and dissemination. A key finding is the presence of a differential homophily effect, where GMO opponents exhibit stronger homophilic tendencies than non-opponents. Despite the prevalence of homophily, this paper uncovers substantial cross-attitude interactions, challenging simplistic notions of echo chambers in GMO risk communication. By integrating entropy and ERGM analyses, this study advances a more nuanced, information-theoretic understanding of how digital platforms mediate public perceptions and debates surrounding controversial socio-scientific issues, offering valuable implications for developing effective risk communication strategies in increasingly polarized online spaces. Full article

This study explores analytical soliton solutions for the cubic–quintic time-fractional nonlinear non-paraxial pulse transmission model. This versatile model finds numerous uses in fiber optic communication, nonlinear optics, and optical signal processing. The strength of the quintic and cubic nonlinear components plays a crucial role in nonlinear processes, such as self-phase modulation, self-focusing, and wave combining. The fractional nonlinear Schrödinger equation (FNLSE) facilitates precise control over the dynamic properties of optical solitons. Exact and methodical solutions include those involving trigonometric functions, Jacobian elliptical functions (JEFs), and the transformation of JEFs into solitary wave (SW) solutions. This study reveals that various soliton solutions, such as periodic, rational, kink, and SW solitons, are identified using the complete discrimination polynomial methods (CDSPM). The concepts of chaos and bifurcation serve as the framework for investigating the system qualitatively. We explore various techniques for detecting chaos, including three-dimensional and two-dimensional graphs, time-series analysis, and Poincarè maps. A sensitivity analysis is performed utilizing a variety of initial conditions. Full article

Social bots increasingly mimic real users and collaborate in large-scale influence campaigns, distorting public perception and making their detection both critical and challenging. Traditional bot detection methods, constrained by single-source features, often fail to capture the complete behavioral and contextual characteristics of social bots, especially their dynamic behavioral evolution and group coordination tactics, resulting in feature incompleteness and reduced detection performance. To address this challenge, we propose CB-MTE, a social bot detection framework based on multi-source heterogeneous feature fusion. CB-MTE adopts a hierarchical architecture: user metadata is used to construct behavioral portraits, deep semantic representations are extracted from textual content via DistilBERT, and community-aware graph embeddings are learned through a combination of random walk and Skip-gram modeling. To mitigate feature redundancy and preserve structural consistency, manifold learning is applied for nonlinear dimensionality reduction, ensuring both local and global topology are maintained. Finally, a CatBoost-based collaborative reasoning mechanism enhances model robustness through ordered target encoding and symmetric tree structures. Experiments on the TwiBot-22 benchmark dataset demonstrate that CB-MTE significantly outperforms mainstream detection models in recognizing dynamic behavioral traits and detecting collaborative bot activities. These results confirm the framework’s capability to capture the complete behavioral and contextual characteristics of social bots through multi-source feature integration. Full article

Advanced Persistent Threats (APTs) challenge cybersecurity due to their stealthy, multi-stage nature. For the provenance graph based on fine-grained kernel logs, existing methods have difficulty distinguishing behavior boundaries and handling complex multi-entity dependencies, which exhibit high false positives in dynamic environments. To address this, we propose a Hypergraph Attention Network framework for APT detection. First, we employ anomaly node detection on provenance graphs constructed from kernel logs to select seed nodes, which serve as starting points for discovering overlapping behavioral communities via node aggregation. These communities are then encoded as hyperedges to construct a hypergraph that captures high-order interactions. By integrating hypergraph structural semantics with nodes and hyperedge dual attention mechanisms, our framework achieves robust APT detection by modeling complex behavioral dependencies. Experiments on DARPA and Unicorn show superior performance: 97.73% accuracy, 98.35% F1-score, and a 0.12% FPR. By bridging hypergraph theory and adaptive attention, the framework effectively models complex attack semantics, offering a robust solution for real-time APT detection. Full article

The increasing demand for real-time multimedia communications has driven the need for highly secure and computationally efficient encryption schemes. In this work, we present a novel chaos-based encryption system that provides remarkable levels of security and performance. It leverages the benefits of applying fast-to-evaluate chaotic maps, along with a 2-Dimensional Look-Up Table approach (2D-LUT), and simple but powerful periodic perturbations. The foundation of our encryption system is a Pseudo-Random Number Generator (PRNG) that consists of a fully connected random graph with M vertices representing chaotic maps that populate the 2D-LUT. In every iteration of the system, one of the M chaotic maps in the graph and the corresponding trajectories are randomly selected from the 2D-LUT using an emulated spin-wheel picker game. This approach exacerbates the complexity in the event of an attack, since the trajectories may come from the same or totally different maps in a non-sequential time order. We additionally perform two levels of perturbation, at the map and trajectory level. The first perturbation (map level) produces new trajectories that are retrieved from the 2D-LUT in non-sequential order and with different initial conditions. The second perturbation applies a p-point crossover scheme to combine a pair of trajectories retrieved from the 2D-LUT and used in the ciphering process, providing higher levels of security. As a final process in our methodology, we implemented a simple packet-based data integrity scheme that detects with high probability if the received information has been modified (for example, by a man-in-the-middle attack). Our results show that our proposed encryption scheme is robust to common cryptanalysis attacks, providing high levels of security and confidentiality while supporting high processing speeds on the order of gigabits per second. To the best of our knowledge, our chaotic cipher implementation is the fastest reported in the literature. Full article

Analyzing how urban ritual spaces transform into everyday living environments is crucial for understanding the spatial structure of contemporary historical districts, particularly in the context of ancestral temples. However, existing research often neglects the integration of both building-level and block-level perspectives when examining such spatial transitions. Grounded in urban morphological principles, we identify the fundamental spatial units of ancestral temples and their surrounding blocks across the early 20th century and the post-1970s era. Using the topological characteristics of an access structure, we construct corresponding network graphs. We then employ embeddedness and conductance metrics to quantify each temple’s changing position within the broader block structure. Moreover, we apply community detection to uncover the structural evolution of clusters in blocks over time. Our findings reveal that, as institutional and cultural factors drive spatial change, ancestral temples exhibit decreased internal cohesion and increased external connectivity. At the block scale, changes in community structure demonstrate how neighborhood clusters transition from a limited number of building-based clusters to everyday living-oriented spatial clusters. These insights highlight the interplay between everyday life demands, land–housing policies, and inherited cultural norms, offering a comprehensive perspective on the secularization of sacred architecture. The framework proposed here not only deepens our understanding of the spatial transformation process but also provides valuable insights for sustainable urban renewal and heritage preservation. Full article

Private consumers, small businesses, and even large enterprises are all at risk from botnets. These botnets are known for spearheading Distributed Denial-Of-Service (DDoS) attacks, spamming large populations of users, and causing critical harm to major organizations. The development of Internet of Things (IoT) devices led to the use of these devices for cryptocurrency mining, in-transit data interception, and sending logs containing private data to the master botnet. Different techniques were developed to identify these botnet activities, but only a few use Graph Neural Networks (GNNs) to analyze host activity by representing their communications with a directed graph. Although GNNs are intended to extract structural graph properties, they risk causing overfitting, which leads to failure when attempting to do so from an unidentified network. In this study, we test the notion that structural graph patterns might be used for efficient botnet detection. In this study, we also present SIR-GN, a structural iterative representation learning methodology for graph nodes. Our approach is built to work well with untested data, and our model is able to provide a vector representation for every node that captures its structural information. Finally, we demonstrate that, when the collection of node representation vectors is incorporated into a neural network classifier, our model outperforms the state-of-the-art GNN-based algorithms in the detection of bot nodes within unknown networks. Full article