Network Analysis Of Data Research Articles

FORECASTING THE RESULTS OF THE PRESIDENTIAL ELECTIONS IN FRANCE BASED ON TWITTER DATA

This paper presents the study to collect, store and analyze data from Twitter to forecast French presidential election results, compared to sociological polls. The first and probably the most important step of the research is to collect, store and clean data, the whole result depends on the amount and quality of data. In the next step of research, datasets are analyzed. Lastly, complete report and visualizations are provided. In the study, we propose modern technics, mathematical algorithms, and machine learning approaches to analyze big amounts of data from the Twitter social network in order to forecast the 2022 French presidential election results. The determined outcome is compared with sociological polls and the real results of elections.
 In the conducted research modern types of media are compared to select the best one for election prediction. Selected Twitter social network as the one with the most appropriate data and availability to download big amounts of useful information. The approach based on the usage of Python programming language, Selenium browser emulation and MongoDB database was used to collect, store and clean data about the main French election candidates – Emmanuel Macron and Marine Le Pen. The research was made from August 2021 until the election itself in April 2022. The determined outcome is compared with sociological polls and the results of elections and showed that analysis of social network data could be a good alternative to traditional sociological polls as it shows the same trends month by month and well predicted the win of Emmanuel Macron in elections. Moreover, the proposed approach has its benefits compared to sociological polls such as always being fresh, and close to real-time information, the price of research is much lower and could be reused for the next parliamentary or presidential elections with a small modification.
 The research could be extended and adapted for other countries. Currently, the proposed algorithms and mathematical models showed good results in the French and Ukraine elections. It works well with English, French, Ukrainian and Russian languages. This allows us to claim that it will also work fine with other Latin or Cyrillic alphabets but for Asian or Arabic languages more research would be needed. Twitter is a good choice for European and American countries. In the future, other social networks should be considered for the countries in which it is not so popular.

Advanced Artificial Intelligence Model for Financial Accounting Transformation Based on Enterprise Unstructured Text Data

As an essential communication medium, the internet brings the freedom and convenience of publishing, transmitting, and acquiring information. At the same time, the problems caused by various kinds of information that endanger social stability and involve the vital interests of the country are also increasingly emerging. The traditional network supervision method can no longer adapt to the continuous development of content security needs. Internet regulators, in the analysis of network data and the retrieval process, mainly focus on structured text data.

Plausible Heterogeneous Graph $k$-Anonymization for Social Networks

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods, aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations. Graph embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data continuously. Publishing social network data not only bring benefit for public health, disaster response, commercial promotion, and many other applications, but also give birth to threats that jeopardize each individual's privacy and security. Unfortunately, most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks. To be specific, attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding. In this paper, we propose a novel link-privacy preserved graph embedding framework using adversarial learning, which can reduce adversary's prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph embedding. Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

Management of hepatocellular carcinomafrom diagnosis in routine clinical practice.

To assess real-world management of patients diagnosed with hepatocellular carcinoma (HCC) within an integrated delivery network. A retrospective cohort analysis of adults newly diagnosed with HCC from January 2014 toMarch2019. Overall survivaland treatment journey were assessed over the entire available follow-up period per patient. Of the 462 patients, 85% had ≥1 treatment. The 24-month overall survival rate (95% CI) from first treatment was 77% (72-82%). Majority of Child-Pugh class A (71%) and B (60%) patients received locoregional therapy first. Half (53.6%) of the patients with liver transplantation first were Child-Pugh class C patients. Sorafenib was the predominant systemic therapy. This integrated delivery network data analysis offers a comprehensive insight into the real-world management of HCC.

An IoT-based smart healthcare system using location-based mesh network and big data analytics

Elderly people requiring care the entire day usually depend on the availability of their family members to give assistance. However, the family members might not provide appropriate help especially in an emergent situation. The application of Internet of Things (IoT) technology with a variety of interconnected devices provides the solution. We propose an IoT-based smart healthcare system comprising wearable devices, which integrates a variety of contact sensors with location-based mesh networks (LBMN) such as Wi-Fi and Bluetooth Low Energy (BLE) connections to continuously sense various parameters of aging people. The BLE-connected devices such as wearable sensors, fixed sensors, seat cushions, pedal mats, magnetic reed switches, and mobile devices are all involved in collecting, processing, and transmitting physiological data and their locations to the cloud. Through the utilization of convenient interfaces such as software applications on smartphones and web pages on computers, it provides real time monitoring of the elderly in terms of localization, activity pattern, and health status. Thus the system enables early detection of health risks to the elderly. We used Platform as a service (PaaS) to receive and store the health data generated from the interconnected devices and to perform analysis. The essential feature of this LBMN is to generate a complete 6W(Who, What,When,Where,Why and How)big data for policy, feed it to the PaaS analysis to easily and quickly obtain more accurate data, and then develop possible health strategy or preventive measures. The proposed healthcare system detected that, out of the 20 participants recruited, 2 persons (10%) were often restless. It was also able to detect abnormal daily activity patterns with more tag positioning and the historical data from the devices. More importantly, it can help to prevent potential physical and neuropsychiatric disorders based on the real-time monitoring information and analyzed historical data for the aging people.

Skin cancer outcomes and risk factors in renal transplant recipients: Analysis of organ procurement and transplantation network data from 2000 to 2021.

Posttransplant skin cancer is the most common malignancy after patients have undergone renal transplantation. Through comprehensive observation with a large sample size nationwide, understanding the risk factors and outcome of posttransplant skin cancer will help to develop appropriate patient surveillance and disease prevention strategies. This retrospective population-based cohort study was based on Organ Procurement and Transplantation Network data released in March 2021. Characteristics and outcomes, including patient survival and graft survival of recipients, were compared. Risk factors for posttransplant skin cancer, cancer onset momentum, and mortality were determined. A total of 199,564 renal transplant recipients were included. After renal transplantation, 7,334 (3.68%), 6,093 (3.05%), and 936 (0.47%) were diagnosed with squamous cell carcinoma, basal cell carcinoma, and melanoma, respectively. Skin cancer was the major cause of death (squamous cell carcinoma: 23.8%, basal cell carcinoma: 18%, and melanoma: 41.6%). Five-year survival rates ranked from best to worst were as follows: basal cell carcinoma (96.7 [95% confidence interval: 96.3-97.2]%), squamous cell carcinoma (94.1 [93.5-94.6]%), melanoma (89.7 [87.7-91.6]%), and cancer-free (87.4 [87.2-87.5]%) (p < 0.001 for all except melanoma vs. cancer-free, p = 0.534). Regarding graft survival, death-censored graft survival, posttransplant skin cancer, and melanoma were significantly better than the cancer-free group (p < 0.001). Independent risk factors for developing posttransplant skin cancer included older age, male sex, Caucasian race, pretransplant malignancy, polycystic kidney disease-induced end-stage renal disease (ESRD), retransplantation, private health insurance, T-cell depletion induction, and tacrolimus/mycophenolic acid use. Caucasian race and pretransplant malignancy were independent risk factors for posttransplant skin cancer onset momentum. Male sex, Caucasian race, pretransplant malignancy, hypertension- or diabetes-induced ESRD, retransplantation, diabetes history, deceased donor, cyclosporin, and mTOR inhibitor use were independent risk factors for posttransplant skin cancer mortality. Although posttransplant skin cancer is a major cause of recipient death, information regarding its impact on patient and graft survival is limited. Given the differences regarding risk factors for posttransplant skin cancer incidence, onset momentum, and mortality, personalized approaches to screening may be appropriate to address the complex issues encountered by kidney transplant recipients.

Functional network: A novel framework for interpretability of deep neural networks

The layered structure of deep neural networks hinders the use of numerous analysis tools and thus the development of its interpretability. Inspired by the success of functional brain networks, we propose a novel framework for interpretability of deep neural networks, that is, the functional network. We construct the functional network of fully connected networks and explore its small-worldness. In our experiments, the mechanisms of regularization methods, namely, batch normalization and dropout, are revealed using graph theoretical analysis and topological data analysis. Our empirical analysis shows the following: (1) batch normalization enhances model performance by increasing the global efficiency and the number of loops but reduces adversarial robustness by lowering the fault tolerance. (2) Dropout improves generalization and robustness of models by improving the functional specialization and fault tolerance. (3) The models with different regularizations can be clustered accurately according to their functional topological differences, reflecting the great potential of the functional network and topological data analysis in interpretability.

Multiagent-Based Data Presentation Mechanism for Multifaceted Analysis in Network Management Tasks.

Although network management tasks are highly automated using big data and artificial intelligence technologies, when an unforeseen cybersecurity problem or fault scenario occurs, administrators sometimes directly analyze system data to make a heuristic decision. However, a wide variety of information is required to address complex cybersecurity risks, whereas current systems are focused on narrowing the candidates of information. In this study, we propose a multiagent-based data presentation mechanism (MADPM) that consists of agents operating data-processing tools that store and analyze network data. Agents in MADPM interact with other agents to form data-processing sequences. In this process, we design not only the composition of the sequence according to requirements, but also a mechanism to expand it to enable multifaceted analysis that supports heuristic reasoning. We tested five case studies in the prototype system implemented in an experimental network. The results indicated that the multifaceted presentation of data can support administrators more than the selected single-faceted optimal presentation. The final outcome of our proposed approach is the provision of a multifaceted and cross-system data presentation for heuristic inference in network management tasks.

The Image of the Modern Regional Leader: Network Analysis Results

The paper is devoted to the analysis of the process of political communication in the conditions of networkization of public space. The sign-symbolic level of political communication is considered on the example of the content-semantic filling of the image of a regional political leader. The purpose of this research is to analyze the content of the political image of the leader and to identify the presence or absence of manifestation of the effect of networking in it. The objectives of the study are to study the goals, the principles of their implementation and the features of communication with other representatives of power and society, which are presented in the content of the image of a political leader. The study uses a set of empirical methods, including non-directional quantitative content-analysis, network data analysis and linguistic analysis. The results of the content analysis are displayed on the tag cloud, and the results of the network analysis are displayed on the thematic graph. The theoretical basis of the study was the theory of the information society and such concepts as “image”, “image-role construct”. According to the results of the study of the text array, which included two large, detailed interviews with the governor of the Nizhny Novgorod region G. S. Nikitin in 2019 and 2020, it was concluded that one of the most common image-role constructs in an interview in 2019 were the following: “leader-industrialist” (aimed at the development of industrial production); “leader-builder” (in particular, he is ready to develop the construction industry of the region); “leader-organizer” (open to new projects and challenges, focused on the successful organization and holding of festive events dedicated to the anniversary of Nizhny Novgorod), “leader-athlete” (advocates for the development of sports in the region). The most common image-role construct in an interview in 2020 was such a meaningful and semantic construct as “leader-manager” (an effective manager who manages the region by coordinating actions with various structural divisions of the government and municipalities). Based on the results of a generalizing analysis, the conclusion was drawn that in the content of the image of a political leader, there was a certain change in the manifestation of the effect of networkization from the polythematic and heterarchy of key topics (in 2019) to the decentralization of the symbolic subject of decision-making and implementation (in 2020).

Network load prediction and anomaly detection using ensemble learning in 5G cellular networks

Network data analytics significantly improved the 5G cellular networks. Data analytics allows network administrators and operators to use the machine and deep learning to analyse the network data efficiently. The standard protocols defined by the 3rd Generation Partnership Project (3GPP) for the network data analytics function are discussed to incorporate into the dataset. The dataset is based on cells in the network considering anomalies and fields of 3GPP, i.e., data rates and information related to the network area. Moreover, machine and deep learning techniques can be used to classify the anomalies. In this regard, we employed Decision trees (DT), Random Forest (RF), Support Vector Machines (SVM) and ensemble learning (EL) to enhance the network prediction performance. For this purpose, we used machine and deep learning techniques, i.e., one-dimensional Convolutional Neural Networks (1D CNN), Multi-Layer Perceptron (MLP), and k-Nearest Neighbours (kNN), respectively. We also used bagging-based three regressors, i.e., 1D CNN, MLP, and kNN, to predict the network load. In addition, we addressed both anomaly detection and load prediction because the presence of anomalies results in high load. The accurate detection of anomalies will result in less network load. Thus, anomalies like a sudden increase in network traffic from a certain cell are also added based on the network traffic pattern to make the dataset more realistic. The simulation results showed that the bagging-based EL outperformed the existing techniques in predicting network load. Moreover, the voting technique outperforms in the case of anomaly detection.

Brain Network Analysis: A Review on Multivariate Analytical Methods.

Despite the explosive growth of neuroimaging studies aimed at analyzing the brain as a complex system, critical methodological gaps remain to be addressed. Most tools currently used for analyzing network data of the brain are univariate in nature and are based on assumptions borne out of previous techniques not directly related to the big and complex data of the brain. Although graph-based methods have shown great promise, the development of principled multivariate models to address inherent limitations of graph-based methods, such as their dependence on network size and degree distributions, and to allow assessing the effects of multiple phenotypes on the brain and simulating brain networks has largely lagged behind. Although some studies have been made in developing multivariate frameworks to fill this gap, in the absence of a "gold-standard" method or guidelines, choosing the most appropriate method for each study can be another critical challenge for investigators in this multidisciplinary field. Here, we briefly introduce important multivariate methods for brain network analyses in two main categories: data-driven and model-based methods. We discuss whether/how such methods are suited for examining connectivity (edge-level), topology (system-level), or both. This review will aid in choosing an appropriate multivariate method with respect to variables such as network type, number of subjects and brain regions included, and the interest in connectivity, topology, or both. This review is aimed to be accessible to investigators from different backgrounds, with a focus on applications in brain network studies, though the methods may be applicable in other areas too. Impact statement As the U.S. National Institute of Health notes, the rich biomedical data can greatly improve our knowledge of human health if new analytical tools are developed, and their applications are broadly disseminated. A major challenge in analyzing the brain as a complex system is about developing parsimonious multivariate methods, and particularly choosing the most appropriate one among the existing methods with respect to the study variables in this multidisciplinary field. This study provides a review on the most important multivariate methods to aid in helping the most appropriate ones with respect to the desired variables for each study.

Basics on network theory to analyze biological systems: a hands-on outlook.

Biological processes result from interactions among molecules and cell-to-cell communications. In the last 50years, network theory has empowered advances in understanding molecular networks' structure and dynamics that regulate biological systems. Adopting a network data analysis point of view at more laboratories might enrich their research capacity to generate forward working hypotheses. This work briefly describes network theory origins and provides basic graph analysis principles in biological systems, specific centrality measurements, and the main models for network structures. Also, we describe a workflow employing user-friendly free platforms to process, construct, and analyze transcriptome data from a network perspective. With this assay, we expect to encourage the implementation of network theory analysis on biological data in everyday laboratory research.

Trends in Adopting Industry 4.0 for Asset Life Cycle Management for Sustainability: A Keyword Co-Occurrence Network Review and Analysis

With the potential of Industry 4.0 technologies to enable sustainable manufacturing, asset life cycle management (ALCM) has been gaining increasing attention in recent years. This study explores the evolution of Industry 4.0 technology applications to sustainable ALCM from 2002 to 2021. This study is based on keywords collected from 3896 ALCM-related scientific articles published in the Web of Science, IEEE Xplore and Engineering Village between 2002 and 2021. We conducted a review analysis of these keywords using a network science-based methodology, which unlike the tedious traditional literature review methods, gives the capability to analyze a huge number of scientific articles efficiently. We built keyword co-occurrence networks (KCNs) from the keywords and explored the network characteristics to uncover meaningful knowledge patterns, knowledge components, knowledge structure, and research trends in the body of literature at the intersection of ALCM and Industry 4.0. The network modeling and data analysis results identify the emerging Industry 4.0-related keywords in ALCM literature and indicate the recent explosion of connectivity among keywords. We found IoT, predictive maintenance and big data to be the top three most popular Industry 4.0-related keywords in ALCM literature. Furthermore, this study maps relevant ALCM keywords in contemporary literature to the nine pillars of Industry 4.0 to help the responsible manufacturing community identify research trends and emerging technologies for sustainability.

Privacy-enhancing data aggregation and data analytics in wireless networks for a large class of distributed queries

Privacy-enhancing techniques and protocols for data aggregation and analytics in wireless networks require the development of novel methods for efficient and privacy-preserving computation of distributed queries with the protection of outcomes from active attackers. Previous approaches to secure privacy-preserving computation of distributed queries incur significant communication overhead and cannot be applied to big data. This paper proposes two solutions to the problem of efficient and privacy-preserving computation of distributed queries with the protection of outcomes from active outsider attackers for a new large class of distributed statistical or numerical queries. This class contains many useful statistics and is larger than other classes considered in the literature previously. We propose two protocols for the Protection of data from Active Attackers (PAA) in the case of distributed privacy-preserving computation: PAA applying Shamir’s Secret Sharing (PAA-SSS) and PAA applying homomorphic encryption (PAA-HE). The PAA-HE protocol combines the use of ElGamal and Paillier encryption schemes in one system. Theoretical analysis and experimental results show that both protocols outperform alternative approaches. PAA-HE provides stronger protection and is more efficient than PAA-SSS.

IPool-Information-Based Pooling in Hierarchical Graph Neural Networks.

With the advent of data science, the analysis of network or graph data has become a very timely research problem. A variety of recent works have been proposed to generalize neural networks to graphs, either from a spectral graph theory or a spatial perspective. The majority of these works, however, focus on adapting the convolution operator to graph representation. At the same time, the pooling operator also plays an important role in distilling multiscale and hierarchical representations, but it has been mostly overlooked so far. In this article, we propose a parameter-free pooling operator, called iPool, that permits to retain the most informative features in arbitrary graphs. With the argument that informative nodes dominantly characterize graph signals, we propose a criterion to evaluate the amount of information of each node given its neighbors and theoretically demonstrate its relationship to neighborhood conditional entropy. This new criterion determines how nodes are selected and coarsened graphs are constructed in the pooling layer. The resulting hierarchical structure yields an effective isomorphism-invariant representation of networked data on arbitrary topologies. The proposed strategy achieves superior or competitive performance in graph classification on a collection of public graph benchmark data sets and superpixel-induced image graph data sets.

Research Status, Hotspots, and Evolutionary Trends of Intelligent Education from the Perspective of Knowledge Graph

Intelligent education research has become a research hotspot in recent years. The Citespace software that operates a graph visualization function was used to clarify the current situation, hot spots, and evolutionary trends of intelligent education research development; the authors, institutions, and countries engaged in intelligent education research, as well as the basic knowledge structure, main keywords, citation clustering, dual-map overlay of journals and citation emergence of intelligent education research. The results show that the annual number of publications in the field has shown an upward trend since 2010, with strong communication among research institutions and countries, but weak communication among researchers. Among them, the United States is the center of the global collaborative network of intelligent education research. The basic knowledge structure of intelligence education research is mainly composed of Classroom Management, Evaluation Index, 5G Network, and Big Data Analytics. The dual-map overlay analysis of journals shows that the core areas of intelligence education are increasing, and the analysis of keywords and cited literature shows that Intelligence Tutoring System, AI system, Students and Education, Model, and System are high-frequency words with high-intensity burstness. In addition, research on intelligent education is characterized by multi-country, multi-field, and multi-disciplinary integration, and the adoption of Big Data, Distance Education Technology and Artificial Intelligence Technology to provide scientific support for teaching and learning will become the key research content in this field in the future.

ML-Based QoE Estimation in 5G Networks Using Different Regression Techniques

Monitoring and providing customers with a satisfying Quality of Experience (QoE) is a crucial business incentive for mobile network operators (MNOs). While the MNO is capable of monitoring a vast amount of network-related key performance indicators (KPIs), it typically does not have access to application-specific performance metrics. Among others, this is due to practical obstacles, such as missing standardized interfaces between the network and the application. Existing QoE models allow to map collected KPIs to the user-perceived quality. However, they are not dynamic, cumbersome to obtain, and often rely on application-level information, such as the stalling duration in the case of video streaming. The 5G networking architecture provides new features which can potentially overcome current limitations of in-network QoE monitoring. More specifically, the Application Function (AF) provides a standardized interface for communicating between 5G systems and third parties, such as application providers. The Network Data Analytics Function (NWDAF) is capable of collecting a vast number of network statistics from other 5G network functions and is dedicated to training and deploying Machine Learning (ML) models. This opens new possibilities, unimaginable for earlier mobile network generations, to dynamically learn the relationship between network KPIs and QoE by utilizing ML. Besides elaborating on how the new capabilities introduced with 5G can support an ML-based QoE estimation, we perform a simulation-based feasibility study which evaluates the estimation accuracy of different state-of-the-art regression techniques. In addition, we discuss them with respect to various qualitative aspects from an MNO’s point of view.

빅데이터를 통해 살펴본 코로나19에 따른 세대별 관광 이동행태 변화

The coronavirus disease-2019 (COVID-19) outbreak has restricted mobility and significantly influenced tourists'' behaviors. This study examines whether different ages and gender play a significant role in travel patterns due to the COVID-19 crisis. Big data analytics in mobile cellular networks were utilized to fully understand the pandemic''s impact on tourists'' mobility and behavioral change. Findings showed that the average tourist activity was highest in their 50s, followed by those in their 20s, 40s, 30s, 60s, teens, and over 70s, from 2018 to 2021. Additionally, in the radius of tourism activity, the tourists'' mobility outside their homes significantly decreased for those in the 60s and older with relatively increased tourism activity. This study also showed a significant difference between men and women, especially in their 40s. Finally, this paper discusses useful implications for future researchers and practitioners from the findings.

Improving Network Representation Learning via Dynamic Random Walk, Self-Attention and Vertex Attributes-Driven Laplacian Space Optimization.

Network data analysis is a crucial method for mining complicated object interactions. In recent years, random walk and neural-language-model-based network representation learning (NRL) approaches have been widely used for network data analysis. However, these NRL approaches suffer from the following deficiencies: firstly, because the random walk procedure is based on symmetric node similarity and fixed probability distribution, the sampled vertices’ sequences may lose local community structure information; secondly, because the feature extraction capacity of the shallow neural language model is limited, they can only extract the local structural features of networks; and thirdly, these approaches require specially designed mechanisms for different downstream tasks to integrate vertex attributes of various types. We conducted an in-depth investigation to address the aforementioned issues and propose a novel general NRL framework called dynamic structure and vertex attribute fusion network embedding, which firstly defines an asymmetric similarity and h-hop dynamic random walk strategy to guide the random walk process to preserve the network’s local community structure in walked vertex sequences. Next, we train a self-attention-based sequence prediction model on the walked vertex sequences to simultaneously learn the vertices’ local and global structural features. Finally, we introduce an attributes-driven Laplacian space optimization to converge the process of structural feature extraction and attribute feature extraction. The proposed approach is exhaustively evaluated by means of node visualization and classification on multiple benchmark datasets, and achieves superior results compared to baseline approaches.

Grouped spatial autoregressive model

With the development of the internet, network data with replications can be collected at different time points. The spatial autoregressive panel (SARP) model is a useful tool for analyzing such network data. However, in the traditional SARP model, all individuals are assumed to be homogeneous in their network autocorrelation coefficients, while in practice, correlations could differ for the nodes in different groups. Here, a grouped spatial autoregressive (GSAR) model based on the SARP model is proposed to permit network autocorrelation heterogeneity among individuals, while analyzing network data with independent replications across different time points and strong spatial effects. Each individual in the network belongs to a latent specific group, which is characterized by a set of parameters. Two estimation methods are studied: two-step naive least-squares estimator, and two-step conditional least-squares estimator. Furthermore, their corresponding asymptotic properties and technical conditions are investigated. To demonstrate the performance of the proposed GSAR model and its corresponding estimation methods, numerical analysis was performed on simulated and real data.