Related references
Note: Only part of the references are listed.
Article
Engineering, Electrical & Electronic
Yusong Zhang et al.
Summary: To address the problem of information leakage in online social networks, this study proposes a deterministic leaker tracking algorithm based on digital fingerprints. The algorithm embeds unique user-identifying information using plug-ins before users access digital media shared by others. Simulation experiments demonstrate that the proposed digital fingerprint fast detection scheme outperforms conventional linear search.
RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING
(2023)
Article
Physics, Multidisciplinary
Yuanhao Huang et al.
Summary: User alignment is important for associating multiple social network accounts of the same user. However, the varying behaviors and friends of the same user across different social networks affect the accuracy of alignment. To mitigate this, a semantically enhanced social network user alignment algorithm (SENUA) is proposed. SENUA aligns users based on attributes, user-generated contents, and check-ins, while reducing local semantic noise by mining semantic features. The algorithm's adaptability to noise is improved using multi-view graph-data augmentation. Furthermore, embedding vectors are optimized using multi-headed graph attention networks and multi-view contrastive learning to enhance aligned users' similar semantic features. Experimental results demonstrate a 6.27% average improvement in hit-precision30, indicating the effectiveness of semantic enhancement in user alignment.
Article
Engineering, Multidisciplinary
Ryan Wen Liu et al.
Summary: Maritime Internet of Things (IoT) has revolutionized the communication between moving vessels in intelligent maritime networks, but the rapid growth of vessel trajectories poses challenges to maritime safety and efficacy. To address this, the proposed AIS data-driven trajectory prediction framework utilizes deep neural networks and dynamic data modeling to accurately and reliably predict vessel trajectories.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Cybernetics
Tong Wang et al.
Summary: Edge computing in vehicles is crucial for improving traffic efficiency in the Internet of Vehicles, but performing collaborative edge computing in social IoV systems presents challenges.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Computer Science, Cybernetics
Tian Wang et al.
Summary: For smart cities, ubiquitous user connectivity and collaborative computation offloading are significant. This article proposes an information prefetching architecture that optimizes collaborative edge computing using a hierarchical data storage and selection strategy. It also utilizes an independent/joint edge-learning model to improve algorithm efficiency and cost-effectiveness.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Computer Science, Cybernetics
Peiying Zhang et al.
Summary: The rapid development of IoT technology accelerates the era of "Internet of everything" and changes the role of network edge devices. Collaborative edge computing (CEC) has emerged to tackle privacy protection and security issues, highlighting the importance of user data security in the IoT ecosystem.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Computer Science, Cybernetics
Ke Zhang et al.
Summary: A social-aware vehicular edge caching mechanism is proposed in this study to dynamically coordinate the cache capability of RSUs and smart vehicles for optimizing caching utility, based on mapping the edge caching system using digital twin technology, constructing a social relation model, and developing the concept of vehicular cache cloud.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Aditya Tandon et al.
Summary: A social network spammer detection technology based on graph convolution networks (GCNs) is proposed to address issues with existing technologies, such as shallow feature extraction and high computational complexity. By combining a network representation learning algorithm with GCN and renormalization technology, local and global structural features of the network can be extracted to effectively detect spam. Experimental results on social networking site data demonstrate the accuracy and efficiency of the proposed method.
IETE JOURNAL OF RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Juan Ni et al.
Summary: Recent studies have shown that attention mechanisms are crucial for accurately capturing user interests in recommender systems. The proposed CCDMA model achieves higher accuracy in extracting user and item latent feature vectors, considering both self-attention and cross-attention, and optimizing a comparative learning framework, leading to significant improvements in various evaluation metrics.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Automation & Control Systems
Phu Pham et al.
Summary: This study introduces a novel dynamic network representation learning model called ComGCN, which can effectively handle the link prediction problem. The model combines node embedding and intracommunity features, demonstrating superior performance compared to recent state-of-the-art baselines on real-world dynamic networks.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Computer Science, Information Systems
Yu Li et al.
Summary: Trust recommendation is an important application of recommendation systems based on social networks. It recommends items based on the trust between users, alleviating data sparseness and improving result interpretability. Existing research mostly assumes trust to be fixed, overlooking changes in trust during interaction. This paper proposes a DDPG-TR algorithm based on deep reinforcement learning to capture changes in user preferences and update trust. Experimental results demonstrate that the DDPG-TR algorithm can provide more accurate recommendation results compared to other algorithms.
Article
Computer Science, Cybernetics
Chenhan Zhang et al.
Summary: An empirical study using digital humanities techniques was conducted on the Chinese historical text "Records of the Three Kingdoms" and its historical novel counterpart "Romance of the Three Kingdoms." The results revealed that the social network in "Romance" is more complex and dynamic than that of "Records," with differences in the influence of the main characters. These findings highlight the different storytelling styles in the two literary genres and the enrichment of literariness in the historical novel through complicated social networks of characters.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2021)
Review
Computer Science, Information Systems
Ash Mohammad Abbas
Summary: This research provides an overview of state-of-the-art research on different applications of social network analysis using deep learning techniques, comparing different schemes based on their focus and features, and pointing out directions for future research.
SOCIAL NETWORK ANALYSIS AND MINING
(2021)
Article
Computer Science, Artificial Intelligence
Hang Dong et al.
Summary: Automated social text annotation involves suggesting tags for shared documents on social media, aiming to improve tag management and document representation. A novel deep learning-based method is proposed, with an attention-based neural network and semantic-based regularization, outperforming state-of-the-art baseline models in terms of F-1 score and training speed. The use of semantic-based loss regularizers boosts the performance of existing models and indicates potential for further improvement with dynamic label semantic matrices.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Information Systems
Ahmad Abbasi et al.
Summary: With the exponential growth in data traffic, the need for a solution that adapts to data changes has arisen. ElStream detects concept drift using ensemble and traditional machine learning techniques, providing better accuracy for different datasets.
Article
Computer Science, Cybernetics
Dawei Zhu et al.
Summary: With the development of industrial intelligence, the article proposes a resource pre-allocation (RPA) method for social media services in smart cities. Through cognitive analytics and multiobjective optimization, the method aims to optimize load balance of edge servers (ESs) in low-latency resource provisioning for various services.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2021)
Article
Computer Science, Information Systems
Stavros Georgousis et al.
Summary: In recent years, there has been a rapid increase in research on graph representation learning in deep learning, with graphs showing great potential in irregular domains. Existing studies have identified challenges in graph deep learning such as dynamic, edge signals, estimation, and generalization, and addressing these challenges will help broaden the application scope of GCNNs.
Article
Communication
Mohammad Shabaz et al.
Summary: With the growth of social networks, the issue of connecting isolated or missing nodes has led to the emergence of link prediction. Various techniques exist to predict optimistic relationships between nodes based on similarity, with the common factor being the evaluation of probability scores for predicting future links. The proposed Shabaz-Urvashi Link Prediction (SULP) technique shows better performance than other link prediction techniques on most testing datasets, as demonstrated through statistical measures such as AUROC, precision, and recall.
JOURNAL OF CREATIVE COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Imad Rida et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Computer Science, Information Systems
Yiteng Pan et al.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Daqi Liu et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Article
Computer Science, Information Systems
Qingtian Zeng et al.
Article
Computer Science, Information Systems
Zaimei Zhang et al.
Article
Computer Science, Information Systems
Na Ta et al.
Proceedings Paper
Computer Science, Theory & Methods
Yongqing Wang et al.
WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019)
(2019)
