Social Network Graph Research Articles

Triangle-induced and degree-wise sampling over large graphs in social networks

Triangle-induced and degree-wise sampling over large graphs in social networks

TRGCN: A Prediction Model for Information Diffusion Based on Transformer and Relational Graph Convolutional Network

In order to capture and integrate the structural features and temporal features contained in social graph and diffusion cascade more effectively, an information diffusion prediction model based on the Transformer and Relational Graph Convolutional Network (TRGCN) is proposed. Firstly, a dynamic heterogeneous graph composed of the social network graph and the diffusion cascade graph was constructed, and it was input into the Relational Graph Convolutional Network (RGCN) to extract the structural features of each node. Secondly, the time embedding of each node was reencoded using Bi-directional Long Short-Term Memory (Bi-LSTM). The time decay function was introduced to give different weights to nodes at different time positions, so as to obtain the temporal features of nodes. Finally, structural features and temporal features were input into Transformer and then merged. The spatiotemporal features are obtained for information diffusion prediction. The experimental results on three real datasets of X (formerly known as Twitter), Douban, and Memetracker show that compared with the optimal model in the comparison experiment, the TRGCN model has an average increase of 4.16% in Hits@100 metric and 13.26% in map@100 metric. The validity and rationality of the model are proved.

Historical Geographical Information System (HGIS): social trajectories of two Chinese historical figures Su Shi and Zuo Zongtang in spatial context

Historical figures have important significance worldwide. This paper introduces the concept of historical Geographical Information System (HGIS) using the lives of two personalities from Chinese history as case studies: Su Shi, a literary figure of the Northern Song Dynasty, and Zuo Zongtang, a military strategist from the late Qing era. By studying the geographical points marking their life activities, their migratory patterns were explored, along with the dynamics of their social networks within time and space, examining the distinctive phases and characteristics of their individual journeys. Kernel density estimation, standard deviation ellipse, location-based distance analysis, and social network graphs were employed in this work. Our findings reveal that Su Shi’s migrations were largely dictated by official appointments, ultimately rooted in imperial successions and factional strife, with his intellectual pursuits significantly influenced by the humanistic milieu. Conversely, Zuo Zongtang’s migrations were predominantly shaped by war, reflecting the challenges of the late Qing era in relation to governance, sovereignty, and diplomacy. The military encampments selected by Zuo Zongtang tended to be situated near water sources, illustrating how his migratory trajectory was influenced by natural geographic conditions. The social circles of these figures are tied to their social and political stature. Through the socio-historic context, the characteristics of these historical figures’ behavioral trajectories relate to the unfolding process of societal and historical development. These insights offer a glimpse into the life journey behind historical figures, implicitly highlighting their perseverance and resilience in adversity, thereby describing innovative approaches to inheriting and disseminating the cultural legacy.

Community detection using Jaya optimization algorithm based on deep learning methods and KNN graph-based clustering

Purpose In this paper, community identification has been considered as the most critical task of social network analysis. The purpose of this paper is to organize the nodes of a given network graph into distinct clusters or known communities. These clusters will therefore form the different communities available within the social network graph. Design/methodology/approach To date, numerous methods have been developed to detect communities in social networks through graph clustering techniques. The k-means algorithm stands out as one of the most well-known graph clustering algorithms, celebrated for its straightforward implementation and rapid processing. However, it has a serious drawback because it is insensitive to initial conditions and always settles on local optima rather than finding the global optimum. More recently, clustering algorithms that use a reciprocal KNN (k-nearest neighbors) graph have been used for data clustering. It skillfully overcomes many major shortcomings of k-means algorithms, especially about the selection of the initial centers of clusters. However, it does face its own challenge: sensitivity to the choice of the neighborhood size parameter k, which is crucial for selecting the nearest neighbors during the clustering process. In this design, the Jaya optimization method is used to select the K parameter in the KNN method. Findings The experiment on real-world network data results show that the proposed approach significantly improves the accuracy of methods in community detection in social networks. On the other hand, it seems to offer some potential for discovering a more refined hierarchy in social networks and thus becomes a useful tool in the analysis of social networks. Originality/value This paper introduces an enhancement to the KNN graph-based clustering method by proposing a local average vector method for selecting the optimal neighborhood size parameter k. Furthermore, it presents an improved Jaya algorithm with KNN graph-based clustering for more effective community detection in social network graphs.

Performance Evaluation of Python Libraries for Community Detection on Large Social Network Graphs

The development of social networking platforms has transformed the way people interact. The increasing number of social media users generates vast amounts of data and creates communities among users that are interesting to analyze. Community detection holds significant benefits in understanding network structures and providing insights into these communities. Community detection can be performed using various libraries and algorithms. However, the abundance of options can be challenging in selecting the appropriate library and algorithm. Therefore, this research evaluates the performance of community detection algorithms on social network graph datasets using several Python libraries such as NetworkX, igraph, Scikit-Network, and CDlib, as well as Louvain and Label Propagation algorithms. The findings of this study reveal that igraph is an ideal library, with fast execution time, efficient memory usage, and user-friendliness. Additionally, the Louvain algorithm is ideal for community detection and exhibits high modularity values.

Combining an improved Apriori algorithm and Social Network analysis to identify the unique sequential features of individual household electricity consumption behaviours

ABSTRACT The household’s electricity consumption behaviour follows a unique sequential pattern and can be identified by analyzing the electricity consumption data with fine granularity in a smart home context. This particular sequence is concretely embodied in a series of electrical activities with temporal association relationships, thus forming a unique household electrical appliance activity-based chain (EAAC). In this study, we propose a method that combines an improved Apriori algorithm and Social Network to construct a household EAACs. First, we improved the Apriori algorithm (Apriori (1,1)) by combining the temporal and transactional sequences and used it to mine the time-series activity associations among different household appliances. After that, we used the Sliding Window concept to splice the time-series associations and obtain the unique EAACs for each household. Next, we visualized the EAACs using the Social Network analysis to reflect the unique sequential features of household electricity consumption behaviours. Finally, the model was validated by analyzing two families’ actual household electricity consumption data, and future research directions were given.

Efficient Parallel D-Core Decomposition at Scale

Directed graphs are prevalent in social networks, web networks, and communication networks. A well-known concept of the directed graph is the D-core, or ( k, l )-core, which is the maximal subgraph in which each vertex has an in-degree not less than k and an out-degree not less than l. Computing the non-empty D-cores for all possible values of k and l , a.k.a. D-core decomposition, has found versatile applications spanning social network analysis, community search, and graph visualization. However, existing algorithms of D-core decomposition suffer from efficiency and scalability issues on large graphs, because serial peeling-based algorithms are limited by single-core utilization, while skyline coreness-based methods exhibit notably high time complexity. To tackle these issues, in this paper, we propose efficient parallel algorithms for D-core decomposition by leveraging the computational prowess of multicore CPUs. Specifically, we first propose a novel algorithm that computes the D-cores for each possible k value, by exploiting an implicit level-by-level vertex removal strategy, which not only diminishes dependencies between vertices but also maintains a time complexity akin to that of sequential algorithms. We further develop an advanced algorithm by introducing a novel concept of D-shell, which allows us to curtail redundant computations by reducing the necessary k values when computing corresponding D-cores, and deriving D-cores with larger k values from the D-cores currently computed based on D-shell. Extensive experiments on ten real-world large graphs show that our algorithms are highly efficient and scalable, and the advanced algorithm is up to two orders of magnitude faster than the state-of-the-art parallel decomposition algorithm with 32 threads.

Experimental analysis and evaluation of cohesive subgraph discovery

Retrieving cohesive subgraphs in networks is a fundamental problem in social network analysis and graph data management. These subgraphs can be used for marketing strategies or recommendation systems. Despite the introduction of numerous models over the years, a systematic comparison of their performance, especially across varied network configurations, remains unexplored. In this study, we evaluated various cohesive subgraph models using task-based evaluations and conducted extensive experimental studies on both synthetic and real-world networks. Thus, we unveil the characteristics of cohesive subgraph models, highlighting their efficiency and applicability. Our findings not only provide a detailed evaluation of current models but also lay the groundwork for future research by shedding light on the balance between the interpretability and cohesion of the subgraphs. This research guides the selection of suitable models for specific analytical needs and applications, providing valuable insights.

Prediction of students’ performance in online learning using supervised machine learning

PurposeThis study leverages social network analysis (SNA) to visualise the way students interacted with online resources and uses the data obtained from SNA as features for supervised machine learning algorithms to predict whether a student will successfully complete a course.Design/methodology/approachThe exploration and visualisation of the data were first carried out to gain a better understanding of the students, the course(s) each student was enrolled in and each course’s virtual learning resources. Following this, the construction of the social network graphs was performed to depict how each student behaved online before the degree centralities were computed for each of the nodes in a social network graph. Data pre-processing to assign labels based on the final result a student obtained in a course was then performed before we trained and tested models to predict which students did or did not graduate.FindingsThe study’s findings demonstrate that the constructed predictive model has good performance, as shown by the accuracy, precision, recall and f-measure metrics. The outcomes also showed that students’ use of online resources is a crucial element that influences how well they perform in their academics.Originality/valueThe similarity index is as low as 9%.

Art Crime Does not pay: Multiplexed Social Network Analysis in Cultural Heritage Trafficking Forensics

Nowadays, crimes connected to cultural heritage can feature as a staple for organised crime networks and act as financial enablers for international conflicts, including terrorism organisations and even inter-state conflicts, in several ways. Goods of cultural significance include a range of valuable objects related to human cultures, like works of art, historical artefacts, and other antiques, but also forgeries based on such objects. These crimes are almost always transnational, for instance, involving theft or looting in one country and goods moved across borders to be sold. This article presents an intelligence methodology based on Social Network Analysis (SNA) techniques that can support law enforcement agencies (LEAs) in their daily struggle against criminals that also pose a threat to national security. The methodology proposed is based on the building of a blended, multiplexed social network graph, deriving from the fusion of a diverse set of data sources, both in the open-source domain (OSINT) and in the classified domain. We will present data collection methods, correlation between sources, possible ways to generate blended links between individuals that retain information from different sources, and SNA techniques applied to intelligence and investigations. The article provides an answer to the following research questions: how we can detect and identify criminal activities and networks related to cultural goods crimes, how we can assist LEAs in countering illicit trafficking, and how we can ensure that art crime does not pay.

A deep semantic-aware approach for Cantonese rumor detection in social networks with graph convolutional network

The rapid development of social networks provides people with opportunities for communication, which also makes it easier for the spread of rumors. In addition to Mandarin Chinese and English rumors, Cantonese rumors have been a major concern on social networks. However, there is no available Cantonese rumor dataset that includes information of propagation structures. Moreover, existing approaches focused on Mandarin Chinese cannot be applied directly to Cantonese rumor detection because of the differences of words in glyphs and pronunciations between them. In this paper, we construct the first Cantonese rumor dataset with abundant propagation structure information. Moreover, a novel deep semantic-aware graph convolutional network is proposed for Cantonese rumor detection, which integrates the global structural information and the local semantic features of Cantonese posts. To be specific, a CantoneseBERT model is designed to encode deep semantic and syntactic representations of Cantonese text contents, which introduces Cantonese glyph and Jyutping embeddings into the inputs of the model. In addition, a Bi-GCN model is used to extract the propagation clues and dispersion information from two social network graphs with opposite directions. Experimental results demonstrate that the proposed model outperforms the state-of-the-art models with an F-score of 0.8686.

SNGPLDP: Social network graph generation based on personalised local differential privacy

SNGPLDP: Social network graph generation based on personalised local differential privacy

Research on Customer Behavior Prediction Model for Cultural Industry Combined with Deep Learning

Abstract In recent years, as deep learning has demonstrated powerful characterization capabilities in the fields of speech, image, and text, researchers have begun to apply it to the field of prediction, i.e., predicting customer behaviors through current interaction records and features. This paper proposes a deep wandering-based customer behavior prediction model that combines deep learning techniques to forecast customer behavioral trends in the cultural industry. The model randomly wanders from the social network graph structure of the customer’s purchase of goods to generate a new behavioral sequence. We regard the user’s behavioral sequence as a word, and we pre-train all the behavioral sequence documents using the Word2vec algorithm model. The experimental comparison revealed that the model, which incorporates the depth-wandering technique, outperforms other models on the test set in terms of predictiveness. The website uses the deep wandering user behavior prediction model to forecast sales and adapts its sales strategy based on the customer’s behavior. 31% of customers were content with the books they bought from the website, while 52% were extremely content. By comparing the book sales before and after applying the model, it was found that the book sales increased significantly after adjusting the sales strategy, indicating that the customer behavior prediction model constructed in this paper can be used practically.

SNGPLDP: Social Network Graph Generation Based on Personalized Local Differential Privacy

SNGPLDP: Social Network Graph Generation Based on Personalized Local Differential Privacy

MLDA: a multi-level k-degree anonymity scheme on directed social network graphs

MLDA: a multi-level k-degree anonymity scheme on directed social network graphs

A new technique for influence maximization on social networks using a moth-flame optimization algorithm

In our modern digital era, social networks have seamlessly integrated into the fabric of our daily lives. These digital platforms serve as vital channels for communication, exchanging information, and cultivating valuable connections. The propagation of information within these social networks has emerged as a central focus for numerous sectors, including politics, marketing, research, education, and finance. Diverse models have been employed to depict the dynamics of information dissemination across these networks. Nevertheless, the notion of influence holds profound significance for both businesses and individuals. Influence maximization, particularly within the context of social networks, has garnered considerable attention owing to its potential to reach and impact a broad audience. This intricate challenge is commonly referred to as the “influence maximization problem,” a problem well-known for its NP-hard complexity. This paper proposes a cutting-edge technique that leverages the Moth-Flame Optimization Algorithm to enhance influence maximization. Influence maximization is an important issue in network analysis, which widely occurs in social networks. Influence can be seen as a cascading effect, where the actions of a few trigger a chain reaction, ultimately reaching a large portion of the network. Identifying these “influencers” is crucial for efficient resource allocation and information dissemination. One of the important issues in finding the maximum influence is choosing the best vertex among all the vertices in the graph. This research presents a new method to find the maximum influence in social networks based on the Moth-Flame Algorithm (MFA). The proposed method aims to find the maximum influence in the social network graph that has a good fitness degree. The algorithm can identify potential influencers. Our simulations across multiple networks have unequivocally showcased the superiority of this algorithm as the preeminent and scalable solution to the influence maximization problem. The experimental outcomes clearly delineate that the employment of the MFA (Maximal First Activation) approach effectively diminishes the execution time required to approximate the maximum influence. The proposed technique improved the accuracy and excucation time by 3.140 % and 12.2 % compared to other methods.

Guarding Your Social Circle: Strategies to Protect Key Connections and Edge Importance

With the growing use of social networks and the consequent rise in the sharing of personal information online, privacy has become a major concern, leading to an increased demand for efficient anonymization techniques. This research proposes innovative methods for hiding information in weighted social network graphs. We provide a topology-modification technique for precisely hiding important nodes in the user network. We also present a differential privacy-based method to safeguard edge weights while taking weight topology correlations into account. With accuracy rates of 87.04% and 94.73%, respectively, our approaches are highly effective in connections to significant nodes and concealing edge weights, respectively. Our methods, which safeguard data integrity to a larger extent than earlier techniques, alter the original graph as little as possible (only 12% of the original edges are changed), as measured by well-known graph metrics. Experiment results on the extracted Instagram posts show that our solutions outperform current approaches in terms of privacy and preserved usefulness.

Dynamics of Opinion Polarization

For decades, researchers have been trying to understand how people form their opinions. This quest has become even more pressing with the widespread usage of online social networks and social media, which seem to amplify the already existing phenomenon of polarization. In this work, we study the problem of polarization assuming that opinions evolve according to the popular Friedkin-Johnsen (FJ) model. The FJ model is one of the few existing opinion dynamics models that has been validated on small/medium-sized social groups. First, we carry out a comprehensive survey of the FJ model in the literature (distinguishing its main variants) and of the many polarization metrics available, deriving an invariant relation among them. Secondly, we derive the conditions under which the FJ variants are able to induce opinion polarization in a social network, as a function of the social ties between the nodes and their individual susceptibility to the opinion of others. Thirdly, we discuss a methodology for finding concrete opinion vectors that are able to bring the network to a polarized state. Finally, our analytical results are applied to two real social network graphs, showing how our theoretical findings can be used to identify polarizing conditions under various configurations.

Hubs of embodied business services in a GVC world

This paper explores the phenomenon of functional upgrading in Global Value Chains (GVCs) by applying empirical techniques of Social Network Analysis and graph theory to data from the TiVA database for the period from 1995 to 2018. Specifically, we focus on two (from less to more complex) stages of GVC participation: the global supply of manufacturing inputs and the global supply of business services to be embodied in other countries’ exports. We identify which countries are the leading specialized global providers in each stage, analysing their evolutions over time and the relationship between both progressions. It highlights the trajectory of China that has increased its role as a hub in both stages to reach top positions. Using a dynamic panel data model, we find that the role of a country as a specialized global supplier of manufacturing inputs is associate with becoming a prominent global supplier of embodied business services, suggesting a path to functional upgrading in GVCs.

A two‐step approach to detect and understand dismisinformation events occurring in social media: A case study with critical times

AbstractThis article describes a novel two‐step approach of detecting and understanding dis/misinformation events in social media that occur during disasters and crisis events. To detect false news events, we designed a deep learning‐based detection algorithm and then trained it with a transfer learning scheme so that the algorithm could decide whether a given group of rumor‐related tweets is a dis/misinformation event. For understanding how dis/misinformation was diffused in social networks and identifying those who are responsible for creating and consuming false information, we present DismisInfoVis, which consists of various visualisations, including a social network graph, a map, line charts, pie charts, and bar charts. By integrating these deep learning and multi‐view visualisation techniques, we could gain a deeper insight into dis/misinformation events in social media from multiple angles. We describe in detail the implementation, training process, and performance evaluations of the detection algorithm and the design and utilization of DismisInfoVis for dis/misinformation data analyses. We hope that this study will contribute to improving the quality of information generated and shared on social media during critical times, eventually helping both the affected and the general public recover from the impacts of disasters and crisis events.