Large-scale dynamic social data representation for structure feature learning

2020 ◽  
Vol 39 (4) ◽  
pp. 5253-5262
Author(s):  
Xiaoxian Zhang ◽  
Jianpei Zhang ◽  
Jing Yang
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Large Scale ◽  
Dynamic Change ◽  
Feature Learning ◽  
Data Representation ◽  
Feature Representation ◽  
Small Scale ◽  
Dynamic Feature ◽  
Dynamic Social Networks

The problems caused by network dimension disasters and computational complexity have become an important issue to be solved in the field of social network research. The existing methods for network feature learning are mostly based on static and small-scale assumptions, and there is no modified learning for the unique attributes of social networks. Therefore, existing learning methods cannot adapt to the dynamic and large-scale of current social networks. Even super large scale and other features. This paper mainly studies the feature representation learning of large-scale dynamic social network structure. In this paper, the positive and negative damping sampling of network nodes in different classes is carried out, and the dynamic feature learning method for newly added nodes is constructed, which makes the model feasible for the extraction of structural features of large-scale social networks in the process of dynamic change. The obtained node feature representation has better dynamic robustness. By selecting the real datasets of three large-scale dynamic social networks and the experiments of dynamic link prediction in social networks, it is found that DNPS has achieved a large performance improvement over the benchmark model in terms of prediction accuracy and time efficiency. When the α value is around 0.7, the model effect is optimal.

Crowd attraction-driven community evolution on social network

2021 ◽  
pp. 2250009
Author(s):  
Fuzhong Nian ◽  
Li Luo ◽  
Xuelong Yu
Keyword(s):  
Social Networks ◽  
Community Structure ◽  
Social Network ◽  
Large Scale ◽  
Detection Algorithm ◽  
Information Propagation ◽  
Evolution Analysis ◽  
Dynamic Social Networks ◽  
Community Evolution ◽  
Community Detection Algorithm

The evolution analysis of community structure of social network will help us understand the composition of social organizations and the evolution of society better. In order to discover the community structure and the regularity of community evolution in large-scale social networks, this paper analyzes the formation process and influencing factors of communities, and proposes a community evolution analysis method of crowd attraction driven. This method uses the traditional community division method to divide the basic community, and introduces the theory of information propagation into complex network to simulate the information propagation of dynamic social networks. Then defines seed node, the activity of basic community and crowd attraction to research the influence of groups on individuals in social networks. Finally, making basic communities as fixed groups in the network and proposing community detection algorithm based on crowd attraction. Experimental results show that the scheme can effectively detect and identify the community structure in large-scale social networks.

Ideology, communication and polarization

2021 ◽  
Vol 376 (1822) ◽  
pp. 20200133
Author(s):  
Yoshihisa Kashima ◽  
Andrew Perfors ◽  
Vanessa Ferdinand ◽  
Elle Pattenden
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Political Discourse ◽  
Network Dynamics ◽  
Political Polarization ◽  
Connectionist Model ◽  
Theme Issue ◽  
Social Network Dynamics ◽  
Dynamic Social Networks ◽  
Echo Chamber

Ideologically committed minds form the basis of political polarization, but ideologically guided communication can further entrench and exacerbate polarization depending on the structures of ideologies and social network dynamics on which cognition and communication operate. Combining a well-established connectionist model of cognition and a well-validated computational model of social influence dynamics on social networks, we develop a new model of ideological cognition and communication on dynamic social networks and explore its implications for ideological political discourse. In particular, we explicitly model ideologically filtered interpretation of social information, ideological commitment to initial opinion, and communication on dynamically evolving social networks, and examine how these factors combine to generate ideologically divergent and polarized political discourse. The results show that ideological interpretation and commitment tend towards polarized discourse. Nonetheless, communication and social network dynamics accelerate and amplify polarization. Furthermore, when agents sever social ties with those that disagree with them (i.e. structure their social networks by homophily), even non-ideological agents may form an echo chamber and form a cluster of opinions that resemble an ideological group. This article is part of the theme issue ‘The political brain: neurocognitive and computational mechanisms’.

Modeling Large-Scale Dynamic Social Networks via Node Embeddings

2019 ◽  
Vol 31 (10) ◽  
pp. 1994-2007 ◽  
Author(s):  
Aakas Zhiyuli ◽  
Xun Liang ◽  
Yanfang Chen ◽  
Xiaoyong Du
Keyword(s):  
Social Networks ◽  
Large Scale ◽  
Dynamic Social Networks ◽  
Node Embeddings

scholarly journals Temporal Activity Path Based Character Correction in Heterogeneous Social Networks via Multimedia Sources

2018 ◽  
Vol 2018 ◽  
pp. 1-16
Author(s):  
Jun Long ◽  
Lei Zhu ◽  
Zhan Yang ◽  
Chengyuan Zhang ◽  
Xinpan Yuan
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Large Scale ◽  
Multimedia Data ◽  
Attribute Information ◽  
Novel Method ◽  
Relationship Network ◽  
Heterogeneous Social Networks ◽  
The Relationship ◽  
Over Time

Vast amount of multimedia data contains massive and multifarious social information which is used to construct large-scale social networks. In a complex social network, a character should be ideally denoted by one and only one vertex. However, it is pervasive that a character is denoted by two or more vertices with different names; thus it is usually considered as multiple, different characters. This problem causes incorrectness of results in network analysis and mining. The factual challenge is that character uniqueness is hard to correctly confirm due to lots of complicated factors, for example, name changing and anonymization, leading to character duplication. Early, limited research has shown that previous methods depended overly upon supplementary attribute information from databases. In this paper, we propose a novel method to merge the character vertices which refer to the same entity but are denoted with different names. With this method, we firstly build the relationship network among characters based on records of social activities participating, which are extracted from multimedia sources. Then we define temporal activity paths (TAPs) for each character over time. After that, we measure similarity of the TAPs for any two characters. If the similarity is high enough, the two vertices should be considered as the same character. Based on TAPs, we can determine whether to merge the two character vertices. Our experiments showed that this solution can accurately confirm character uniqueness in large-scale social network.

Visualizing Co-Authorship Social Networks and Collaboration Recommendations With CNARe

2018 ◽  
pp. 173-188
Author(s):  
Michele A. Brandão ◽  
Matheus A. Diniz ◽  
Guilherme A. de Sousa ◽  
Mirella M. Moro
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Large Scale ◽  
Online Tool ◽  
Strength Of Ties ◽  
E Learning

Studies have analyzed social networks considering a plethora of metrics for different goals, from improving e-learning to recommend people and things. Here, we focus on large-scale social networks defined by researchers and their common published articles, which form co-authorship social networks. Then, we introduce CNARe, an online tool that analyzes the networks and present recommendations of collaborations based on three different algorithms (Affin, CORALS and MVCWalker). Through visualizations and social networks metrics, CNARe also allows to investigate how the recommendations affect the co-authorship social networks, how researchers' networks are in a central and eagle-eye context, and how the strength of ties behaves in large co-authorship social networks. Furthermore, users can upload their own network in CNARe and make their own recommendation and social network analysis.

Extending Social Network Diagrams for Large Scale Collaboration

2012 ◽  
pp. 1-13
Author(s):  
I.T. Hawryszkiewycz
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Web 2.0 ◽  
Large Scale ◽  
Policy Planning ◽  
Web 2.0 Technologies ◽  
Enterprise Social Networks ◽  
Cloud Technologies ◽  
Common Vision ◽  
Network Diagrams

The chapter provides a way for modeling large scale collaboration using an extension to social network diagrams called enterprise social networks (ESNs). The chapter uses the ESN diagrams to describe activities in policy planning and uses these to define the services to be provided by cloud technologies to support large scale collaboration. This chapter describes collaboration by an architecture made up of communities each with a role to ensure that collaboration is sustainable. The architecture is based on the idea of an ensemble of communities all working to a common vision supported by services provided by the collaboration cloud using Web 2.0 technologies.

scholarly journals Private algorithms for the protected in social network search

2016 ◽  
Vol 113 (4) ◽  
pp. 913-918 ◽  
Author(s):  
Michael Kearns ◽  
Aaron Roth ◽  
Zhiwei Steven Wu ◽  
Grigory Yaroslavtsev
Keyword(s):  
Infectious Disease ◽  
Social Networks ◽  
Social Network ◽  
Data Privacy ◽  
Large Scale ◽  
Graph Search ◽  
Medical Testing ◽  
Background Checks ◽  
Network Search ◽  
Natural Variants

Motivated by tensions between data privacy for individual citizens and societal priorities such as counterterrorism and the containment of infectious disease, we introduce a computational model that distinguishes between parties for whom privacy is explicitly protected, and those for whom it is not (the targeted subpopulation). The goal is the development of algorithms that can effectively identify and take action upon members of the targeted subpopulation in a way that minimally compromises the privacy of the protected, while simultaneously limiting the expense of distinguishing members of the two groups via costly mechanisms such as surveillance, background checks, or medical testing. Within this framework, we provide provably privacy-preserving algorithms for targeted search in social networks. These algorithms are natural variants of common graph search methods, and ensure privacy for the protected by the careful injection of noise in the prioritization of potential targets. We validate the utility of our algorithms with extensive computational experiments on two large-scale social network datasets.

Prediction of Social Influence for Provenance of Misinformation in Online Social Network Using Big Data Approach

2020 ◽  
Author(s):  
Kumaran P ◽  
Rajeswari Sridhar
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Law Enforcement ◽  
Online Social Networks ◽  
Large Scale ◽  
Online Social Network ◽  
Root Cause ◽  
Minimum Number ◽  
Targeted Marketing ◽  
Implicit And Explicit

Abstract Online social networks (OSNs) is a platform that plays an essential role in identifying misinformation like false rumors, insults, pranks, hoaxes, spear phishing and computational propaganda in a better way. Detection of misinformation finds its applications in areas such as law enforcement to pinpoint culprits who spread rumors to harm the society, targeted marketing in e-commerce to identify the user who originates dissatisfaction messages about products or services that harm an organizations reputation. The process of identifying and detecting misinformation is very crucial in complex social networks. As misinformation in social network is identified by designing and placing the monitors, computing the minimum number of monitors for detecting misinformation is a very trivial work in the complex social network. The proposed approach determines the top suspected sources of misinformation using a tweet polarity-based ranking system in tandem with sarcasm detection (both implicit and explicit sarcasm) with optimization approaches on large-scale incomplete network. The algorithm subsequently uses this determined feature to place the minimum set of monitors in the network for detecting misinformation. The proposed work focuses on the timely detection of misinformation by limiting the distance between the suspected sources and the monitors. The proposed work also determines the root cause of misinformation (provenance) by using a combination of network-based and content-based approaches. The proposed work is compared with the state-of-art work and has observed that the proposed algorithm produces better results than existing methods.

scholarly journals Finding Potential Propagators and Customers in Location-Based Social Networks: An Embedding-Based Approach

2020 ◽  
Vol 10 (22) ◽  
pp. 8003
Author(s):  
Yi-Chun Chen ◽  
Cheng-Te Li
Keyword(s):  
Social Networks ◽  
Large Scale ◽  
Main Idea ◽  
Feature Representation ◽  
Specific Point ◽  
Point Of Interest ◽  
The Future ◽  
Location Based Social Networks ◽  
Low Dimensional ◽  
Embedding Methods

In the scenarios of location-based social networks (LBSN), the goal of location promotion is to find information propagators to promote a specific point-of-interest (POI). While existing studies mainly focus on accurately recommending POIs for users, less effort is made for identifying propagators in LBSN. In this work, we propose and tackle two novel tasks, Targeted Propagator Discovery (TPD) and Targeted Customer Discovery (TCD), in the context of Location Promotion. Given a target POI l to be promoted, TPD aims at finding a set of influential users, who can generate more users to visit l in the future, and TCD is to find a set of potential users, who will visit l in the future. To deal with TPD and TCD, we propose a novel graph embedding method, LBSN2vec. The main idea is to jointly learn a low dimensional feature representation for each user and each location in an LBSN. Equipped with learned embedding vectors, we propose two similarity-based measures, Influential and Visiting scores, to find potential targeted propagators and customers. Experiments conducted on a large-scale Instagram LBSN dataset exhibit that LBSN2vec and its variant can significantly outperform well-known network embedding methods in both tasks.

Sign in / Sign up

Export Citation Format

Share Document