scholarly journals Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data †

Information ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 306
Author(s):  
Nikolaus Nova Parulian ◽  
Tiffany Lu ◽  
Shubhanshu Mishra ◽  
Mihai Avram ◽  
Jana Diesner
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Information Diffusion ◽  
Social Systems ◽  
Target Function ◽  
Centrality Measures ◽  
Network Data ◽  
Social Network Data ◽  
Empirical Networks ◽  
The Impact

Observed social networks are often considered as proxies for underlying social networks. The analysis of observed networks oftentimes involves the identification of influential nodes via various centrality measures. This paper brings insights from research on adversarial attacks on machine learning systems to the domain of social networks by studying strategies by which an adversary can minimally perturb the observed network structure to achieve their target function of modifying the ranking of a target node according to centrality measures. This can represent the attempt of an adversary to boost or demote the degree to which others perceive individual nodes as influential or powerful. We study the impact of adversarial attacks on targets and victims, and identify metric-based security strategies to mitigate such attacks. We conduct a series of controlled experiments on synthetic network data to identify attacks that allow the adversary to achieve their objective with a single move. We then replicate the experiments with empirical network data. We run our experiments on common network topologies and use common centrality measures. We identify a small set of moves that result in the adversary achieving their objective. This set is smaller for decreasing centrality measures than for increasing them. For both synthetic and empirical networks, we observe that larger networks are less prone to adversarial attacks than smaller ones. Adversarial moves have a higher impact on cellular and small-world networks, while random and scale-free networks are harder to perturb. Also, empirical networks are harder to attack than synthetic networks. Using correlation analysis on our experimental results, we identify how combining measures with low correlation can aid in reducing the effectiveness of adversarial moves. Our results also advance the knowledge about the robustness of centrality measures to network perturbations. The notion of changing social network data to yield adversarial outcomes has practical implications, e.g., for information diffusion on social media, influence and power dynamics in social systems, and developing solutions to improving network security.

Mining of Leaders in Mobile Telecom Social Networks

2016 ◽  
pp. 68-77
Author(s):  
Mantian (Mandy) Hu
Keyword(s):  
Social Networks ◽  
Big Data ◽  
Social Network ◽  
Information Diffusion ◽  
Network Data ◽  
Massive Datasets ◽  
Social Network Data ◽  
The Social ◽  
Marketing Efficiency ◽  
Mobile Telecom

In the age of Big Data, the social network data collected by telecom operators are growing exponentially. How to exploit these data and mine value from them is an important issue. In this article, an accurate marketing strategy based on social network is proposed. The strategy intends to help telecom operators to improve their marketing efficiency. This method is based on mutual peers' influence in social network, by identifying the influential users (leaders). These users can promote the information diffusion prominently. A precise marketing is realized by taking advantage of the user's influence. Data were collected from China Mobile and analyzed. For the massive datasets, the Apache Spark was chosen for its good scalability, effectiveness and efficiency. The result shows a great increase of the telecom traffic, compared with the result without leader identification.

scholarly journals Analyzing the Effect of Negation in Sentiment Polarity of Facebook Dialectal Arabic Text

2021 ◽  
Vol 11 (11) ◽  
pp. 4768
Author(s):  
Sanaa Kaddoura ◽  
Maher Itani ◽  
Chris Roast
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Sentiment Analysis ◽  
Arabic Language ◽  
Network Data ◽  
Arabic Text ◽  
Social Network Data ◽  
Dialectal Arabic ◽  
The Impact ◽  
Modern Standard

With the increase in the number of users on social networks, sentiment analysis has been gaining attention. Sentiment analysis establishes the aggregation of these opinions to inform researchers about attitudes towards products or topics. Social network data commonly contain authors’ opinions about specific subjects, such as people’s opinions towards steps taken to manage the COVID-19 pandemic. Usually, people use dialectal language in their posts on social networks. Dialectal language has obstacles that make opinion analysis a challenging process compared to working with standard language. For the Arabic language, Modern Standard Arabic tools (MSA) cannot be employed with social network data that contain dialectal language. Another challenge of the dialectal Arabic language is the polarity of opinionated words affected by inverters, such as negation, that tend to change the word’s polarity from positive to negative and vice versa. This work analyzes the effect of inverters on sentiment analysis of social network dialectal Arabic posts. It discusses the different reasons that hinder the trivial resolution of inverters. An experiment is conducted on a corpus of data collected from Facebook. However, the same work can be applied to other social network posts. The results show the impact that resolution of negation may have on the classification accuracy. The results show that the F1 score increases by 20% if negation is treated in the text.

scholarly journals Retweet Prediction Based on User Behavior

2021 ◽  
Author(s):  
Syeda Nadia Firdaus
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Network ◽  
Prediction Model ◽  
Matrix Factorization ◽  
Information Diffusion ◽  
User Behavior ◽  
Past Research ◽  
The Difference ◽  
The Impact

Social network is a hot topic of interest for researchers in the field of computer science in recent years. These social networks such as Facebook, Twitter, Instagram play an important role in information diffusion. Social network data are created by its users. Users’ online activities and behavior have been studied in various past research efforts in order to get a better understanding on how information is diffused on social networks. In this study, we focus on Twitter and we explore the impact of user behavior on their retweet activity. To represent a user’s behavior for predicting their retweet decision, we introduce 10-dimentional emotion and 35-dimensional personality related features. We consider the difference of a user being an author and a retweeter in terms of their behaviors, and propose a machine learning based retweet prediction model considering this difference. We also propose two approaches for matrix factorization retweet prediction model which learns the latent relation between users and tweets to predict the user’s retweet decision. In the experiment, we have tested our proposed models. We find that models based on user behavior related features provide good improvement (3% - 6% in terms of F1- score) over baseline models. By only considering user’s behavior as a retweeter, the data processing time is reduced while the prediction accuracy is comparable to the case when both retweeting and posting behaviors are considered. In the proposed matrix factorization models, we include tweet features into the basic factorization model through newly defined regularization terms and improve the performance by 3% - 4% in terms of F1-score. Finally, we compare the performance of machine learning and matrix factorization models for retweet prediction and find that none of the models is superior to the other in all occasions. Therefore, different models should be used depending on how prediction results will be used. Machine learning model is preferable when a model’s performance quality is important such as for tweet re-ranking and tweet recommendation. Matrix factorization is a preferred option when model’s positive retweet prediction capability is more important such as for marketing campaign and finding potential retweeters.

scholarly journals Retweet Prediction Based on User Behavior

2021 ◽  
Author(s):  
Syeda Nadia Firdaus
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Network ◽  
Prediction Model ◽  
Matrix Factorization ◽  
Information Diffusion ◽  
User Behavior ◽  
Past Research ◽  
The Difference ◽  
The Impact

Social network is a hot topic of interest for researchers in the field of computer science in recent years. These social networks such as Facebook, Twitter, Instagram play an important role in information diffusion. Social network data are created by its users. Users’ online activities and behavior have been studied in various past research efforts in order to get a better understanding on how information is diffused on social networks. In this study, we focus on Twitter and we explore the impact of user behavior on their retweet activity. To represent a user’s behavior for predicting their retweet decision, we introduce 10-dimentional emotion and 35-dimensional personality related features. We consider the difference of a user being an author and a retweeter in terms of their behaviors, and propose a machine learning based retweet prediction model considering this difference. We also propose two approaches for matrix factorization retweet prediction model which learns the latent relation between users and tweets to predict the user’s retweet decision. In the experiment, we have tested our proposed models. We find that models based on user behavior related features provide good improvement (3% - 6% in terms of F1- score) over baseline models. By only considering user’s behavior as a retweeter, the data processing time is reduced while the prediction accuracy is comparable to the case when both retweeting and posting behaviors are considered. In the proposed matrix factorization models, we include tweet features into the basic factorization model through newly defined regularization terms and improve the performance by 3% - 4% in terms of F1-score. Finally, we compare the performance of machine learning and matrix factorization models for retweet prediction and find that none of the models is superior to the other in all occasions. Therefore, different models should be used depending on how prediction results will be used. Machine learning model is preferable when a model’s performance quality is important such as for tweet re-ranking and tweet recommendation. Matrix factorization is a preferred option when model’s positive retweet prediction capability is more important such as for marketing campaign and finding potential retweeters.

Classifying the Influential Individuals in Multi-Layer Social Networks

2019 ◽  
Vol 8 (1) ◽  
pp. 21-32
Author(s):  
Ruchi Mittal ◽  
M.P.S Bhatia
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Information Diffusion ◽  
Real Life ◽  
Single Layer ◽  
Machine Learning Techniques ◽  
Centrality Measures ◽  
Learning Techniques ◽  
Modes Of Interaction ◽  
Source Of Information

Nowadays, social media is one of the popular modes of interaction and information diffusion. It is commonly found that the main source of information diffusion is done by some entities and such entities are also called as influencers. An influencer is an entity or individual who has the ability to influence others because of his/her relationship or connection with his/her audience. In this article, we propose a methodology to classify influencers from multi-layer social networks. A multi-layer social network is the same as a single layer social network depict that it includes multiple properties of a node and modeled them into multiple layers. The proposed methodology is a fusion of machine learning techniques (SVM, neural networks and so on) with centrality measures. We demonstrate the proposed algorithm on some real-life networks to validate the effectiveness of the approach in multi-layer systems.

Network Redundancy and Information Diffusion: The Impacts of Information Redundancy, Similarity, and Tie Strength

2016 ◽  
Vol 46 (2) ◽  
pp. 250-272 ◽  
Author(s):  
Hai Liang ◽  
King-wa Fu
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Information Diffusion ◽  
Tie Strength ◽  
Information Redundancy ◽  
Ego Networks ◽  
Core Concepts ◽  
The Impact

It remains controversial whether community structures in social networks are beneficial or not for information diffusion. This study examined the relationships among four core concepts in social network analysis—network redundancy, information redundancy, ego-alter similarity, and tie strength—and their impacts on information diffusion. By using more than 6,500 representative ego networks containing nearly 1 million following relationships from Twitter, the current study found that (1) network redundancy is positively associated with the probability of being retweeted even when competing variables are controlled for; (2) network redundancy is positively associated with information redundancy, which in turn decreases the probability of being retweeted; and (3) the inclusion of both ego-alter similarity and tie strength can attenuate the impact of network redundancy on the probability of being retweeted.

scholarly journals Questions and features of automated social networks monitoring with support of intelligent user messages analysis.

2014 ◽  
Vol 2014 (4) ◽  
pp. 146-152 ◽  
Author(s):  
Александр Подвесовский ◽  
Aleksandr Podvesovskiy ◽  
Дмитрий Будыльский ◽  
Dmitriy Budylskiy
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Text Mining ◽  
Sentiment Analysis ◽  
Opinion Mining ◽  
Software Implementation ◽  
Network Data ◽  
Research Directions ◽  
Social Network Data ◽  
Monitoring Model

An opinion mining monitoring model for social networks introduced. The model includes text mining processing over social network data and uses sentiment analysis approach in particular. Practical usage results of software implementation and its requirements described as well as further research directions.

Network Basics: Points, Lines, and Positions

2020 ◽  
pp. 15-33
Author(s):  
Ryan Light ◽  
James Moody
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Network Analysis ◽  
Ethical Issues ◽  
Building Blocks ◽  
Levels Of Analysis ◽  
Network Data ◽  
Social Network Data ◽  
Basic Concepts ◽  
Statistical Approaches

This chapter presents an introduction to the basic concepts central to social network analysis. Written for those with little experience in the approach, the chapter aims to provide the necessary tools to dig deeper into exploring social networks via the subsequent chapters in this volume. It begins by introducing the building blocks of networks—nodes and edges—and their characteristics. Next, it outlines several of the major dimensions of network analysis, including the implications of boundary specification and levels of analysis. It also briefly introduces statistical approaches to networks and network data collection. The chapter concludes with a discussion of ethical issues that arise when collecting and analyzing social network data.

scholarly journals Edge overlap in weighted and directed social networks

2021 ◽  
pp. 1-15
Author(s):  
Heather Mattie ◽  
Jukka-Pekka Onnela
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Social Interactions ◽  
Network Data ◽  
Directed Networks ◽  
Rural Villages ◽  
Social Network Data ◽  
Structure Strength ◽  
Mean And Variance ◽  
The Mean

Abstract With the increasing availability of behavioral data from diverse digital sources, such as social media sites and cell phones, it is now possible to obtain detailed information about the structure, strength, and directionality of social interactions in varied settings. While most metrics of network structure have traditionally been defined for unweighted and undirected networks only, the richness of current network data calls for extending these metrics to weighted and directed networks. One fundamental metric in social networks is edge overlap, the proportion of friends shared by two connected individuals. Here, we extend definitions of edge overlap to weighted and directed networks and present closed-form expressions for the mean and variance of each version for the Erdős–Rényi random graph and its weighted and directed counterparts. We apply these results to social network data collected in rural villages in southern Karnataka, India. We use our analytical results to quantify the extent to which the average overlap of the empirical social network deviates from that of corresponding random graphs and compare the values of overlap across networks. Our novel definitions allow the calculation of edge overlap for more complex networks, and our derivations provide a statistically rigorous way for comparing edge overlap across networks.

Sign in / Sign up

Export Citation Format

Share Document