scholarly journals Cross-Modal Search for Social Networks via Adversarial Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Nan Zhou ◽  
Junping Du ◽  
Zhe Xue ◽  
Chong Liu ◽  
Jinxuan Li
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Information Search ◽  
State Of The Art ◽  
Visual Features ◽  
Adversarial Learning ◽  
Sina Weibo ◽  
Modal Data ◽  
Social Network Data ◽  
Correlation Learning

Cross-modal search has become a research hotspot in the recent years. In contrast to traditional cross-modal search, social network cross-modal information search is restricted by data quality for arbitrary text and low-resolution visual features. In addition, the semantic sparseness of cross-modal data from social networks results in the text and visual modalities misleading each other. In this paper, we propose a cross-modal search method for social network data that capitalizes on adversarial learning (cross-modal search with adversarial learning: CMSAL). We adopt self-attention-based neural networks to generate modality-oriented representations for further intermodal correlation learning. A search module is implemented based on adversarial learning, through which the discriminator is designed to measure the distribution of generated features from intramodal and intramodal perspectives. Experiments on real-word datasets from Sina Weibo and Wikipedia, which have similar properties to social networks, show that the proposed method outperforms the state-of-the-art cross-modal search methods.

scholarly journals I Know Where You Are Coming From: On the Impact of Social Media Sources on AI Model Performance (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13971-13972
Author(s):  
Yang Qi ◽  
Farseev Aleksandr ◽  
Filchenkov Andrey
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Model Performance ◽  
User Profiling ◽  
Personalized Recommendation ◽  
Modal Data ◽  
Social Media Networks ◽  
The Impact

Nowadays, social networks play a crucial role in human everyday life and no longer purely associated with spare time spending. In fact, instant communication with friends and colleagues has become an essential component of our daily interaction giving a raise of multiple new social network types emergence. By participating in such networks, individuals generate a multitude of data points that describe their activities from different perspectives and, for example, can be further used for applications such as personalized recommendation or user profiling. However, the impact of the different social media networks on machine learning model performance has not been studied comprehensively yet. Particularly, the literature on modeling multi-modal data from multiple social networks is relatively sparse, which had inspired us to take a deeper dive into the topic in this preliminary study. Specifically, in this work, we will study the performance of different machine learning models when being learned on multi-modal data from different social networks. Our initial experimental results reveal that social network choice impacts the performance and the proper selection of data source is crucial.

Social Networks and Crime: Pitfalls and Promises for Advancing the Field

2019 ◽  
Vol 2 (1) ◽  
pp. 99-122 ◽  
Author(s):  
Katherine Faust ◽  
George E. Tita
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Potential Measurement ◽  
Fully Integrated ◽  
Social Network Data ◽  
The Past ◽  
Dynamic Social Network ◽  
Criminological Research ◽  
The Social ◽  
Criminological Theories

Over the past decade, a considerable literature has emerged within criminology stemming from the collection of social network data and the adoption of social network analysis by a cadre of scholars. We review recent contributions to four areas of crime research: co-offending networks, illicit networks, gang-rivalry networks, and neighborhoods and crime. Our review highlights potential pitfalls that one might encounter when using social networks in criminological research and points to fruitful directions for further research. In particular, we recommend paying special attention to the clear specifications of what ties in the network are assumed to be doing, potential measurement weaknesses that can arise when using police or investigative data to construct a network, and understanding dynamic social network processes related to criminological outcomes. We envision a bright future in which the social network perspective will be more fully integrated into criminological theories, analyses, and applications.

Genetic Algorithm Applied in the Social Network Data Analysis

2013 ◽  
Vol 427-429 ◽  
pp. 2188-2191
Author(s):  
Lei Liu ◽  
Quan Bao Gao
Keyword(s):  
Genetic Algorithm ◽  
Social Networks ◽  
Social Network ◽  
Data Analysis ◽  
Rapid Development ◽  
Virtual Community ◽  
Social Network Data ◽  
Starting Point ◽  
The Social ◽  
Optimal Data Analysis

The rapid development of network and information technology makes the network become the indispensable part in people's life. Network design uses email as a starting point, instead of actual letters. Then Happy Nets, BBS etc. are evolved from it, with virtual as their major feature. In the process of social networks evolution, the personal image transformed from the actual into the virtual one. All this has contributed to the birth of the social network, which then makes the contacts among people presenting the feature of network expansion and cost reduction. The popular social network nowadays is considered to be social plus network, namely, through the network, as a carrier, people are connected to form a virtual community with certain characteristics. Based on the genetic algorithm and genetic coding technology, the article is designed to make the optimal data analysis and create a optimistic cyber environment in the process of the social networks explosive development.

Incorporating Trust Relation with PMF to Enhance Social Network Recommendation Performance

2016 ◽  
Vol 30 (06) ◽  
pp. 1659016 ◽  
Author(s):  
Hui Li ◽  
Xiao-Ping Ma ◽  
Jun Shi
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Social Network Analysis ◽  
Network Analysis ◽  
Matrix Factorization ◽  
Web Applications ◽  
State Of The Art ◽  
Large Datasets ◽  
Trust Relation ◽  
The Empirical Analysis

In view of the exponential growth of information generated by social networks, social network analysis and recommendation have become important for many web applications. This paper examines the problem of social collaborative filtering to recommend items of interest to users in a social network setting. Many social networks capture the relationships among the nodes by using trust scores to label the edges. The bias of a node denotes its propensity to trust/mistrust its neighbors and is closely related to truthfulness. It is based on the idea that the recommendation of a highly biased node should be removed. In this paper, we propose a model-based approach for recommendation employing matrix factorization after removing the bias nodes from each link, which naturally fuses the users’ tastes and their trusted friends’ favors together. The empirical analysis on real large datasets demonstrate that our approaches outperform other state-of-the-art methods.

scholarly journals Co-authorship prediction in academic social network

2019 ◽  
Author(s):  
William Takahiro Maruyama ◽  
Luciano Antonio Digiampietri
Keyword(s):  
Artificial Intelligence ◽  
Social Networks ◽  
Social Network ◽  
State Of The Art ◽  
The State ◽  
Artificial Intelligence Techniques ◽  
Academic Social Network ◽  
Academic Social Networks

The prediction of relationships in a social network is a complex and extremely useful task to enhance or maximize collaborations by indicating the most promising partnerships. In academic social networks, prediction of relationships is typically used to try to identify potential partners in the development of a project and/or co-authors for publishing papers. This paper presents an approach to predict coauthorships combining artificial intelligence techniques with the state-of-the-art metrics for link predicting in social networks.

scholarly journals Image Based Classification of Rumor Information from the Social Network Platform

2021 ◽  
Vol 38 (5) ◽  
pp. 1413-1421
Author(s):  
Vallamchetty Sreenivasulu ◽  
Mohammed Abdul Wajeed
Keyword(s):  
Social Networks ◽  
Social Network ◽  
End Users ◽  
Web Based ◽  
Suggested Approach ◽  
Text Input ◽  
Social Network Data ◽  
Proposed Model ◽  
Spam Filters ◽  
Network Platform

Spam emails based on images readily evade text-based spam email filters. More and more spammers are adopting the technology. The essence of email is necessary in order to recognize image content. Web-based social networking is a method of communication between the information owner and end users for online exchanges that use social network data in the form of images and text. Nowadays, information is passed on to users in shorter time using social networks, and the spread of fraudulent material on social networks has become a major issue. It is critical to assess and decide which features the filters require to combat spammers. Spammers also insert text into photographs, causing text filters to fail. The detection of visual garbage material has become a hotspot study on spam filters on the Internet. The suggested approach includes a supplementary detection engine that uses visuals as well as text input. This paper proposed a system for the assessment of information, the detection of information on fraud-based mails and the avoidance of distribution to end users for the purpose of enhancing data protection and preventing safety problems. The proposed model utilizes Machine Learning and Convolutional Neural Network (CNN) methods to recognize and prevent fraud information being transmitted to end users.

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.

Fuzzy-Based Techniques in Human-Like Processing of Social Network Data

2015 ◽  
Vol 23 (Suppl. 1) ◽  
pp. 1-14 ◽  
Author(s):  
Lotfi A. Zadeh ◽  
Ali M. Abbasov ◽  
Shahnaz N. Shahbazova
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Fuzzy Sets ◽  
Possibility Theory ◽  
Linguistic Terms ◽  
Social Network Data ◽  
Processing Data ◽  
Source Of Information ◽  
Analysis Of Social Networks ◽  
Theory Of Fuzzy Sets

Social networks have gained a lot attention. They are perceived as a vast source of information about their users. Variety of different methods and techniques has been proposed to analyze these networks in order to extract valuable information about the users – things they do and like/dislike. A lot of effort is put into improvement of analytical methods in order to grasp a more accurate and detailed image of users. Such information would have an impact on many aspects of everyday life of people – from politics, via professional life, to shopping and entertainment. The theory of fuzzy sets and systems, introduced in 1965, has the ability to handle imprecise and ambiguous information, and to cope with linguistic terms. The theory has evolved into such areas like possibility theory and computing with words. It is very suitable for processing data in a human-like way, and providing the results in a human-oriented manner. The paper presents a short survey of works that use fuzzy-based technologies for analysis of social networks. We pose an idea that fuzzy-based techniques allow for introduction of humancentric and human-like data analysis processes. We include here detailed descriptions of a few target areas of social network analysis that could benefit from applications of fuzzy sets and systems methods.

scholarly journals Structural Attack to Anonymous Graph of Social Networks

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Tieying Zhu ◽  
Shanshan Wang ◽  
Xiangtao Li ◽  
Zhiguo Zhou ◽  
Riming Zhang
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Graph Matching ◽  
Rapid Development ◽  
Sensitive Information ◽  
Matching Method ◽  
Graph Data ◽  
Social Network Data ◽  
Regional Feature ◽  
Social Graphs

With the rapid development of social networks and its applications, the demand of publishing and sharing social network data for the purpose of commercial or research is increasing. However, the disclosure risks of sensitive information of social network users are also arising. The paper proposes an effective structural attack to deanonymize social graph data. The attack uses the cumulative degree ofn-hop neighbors of a node as the regional feature and combines it with the simulated annealing-based graph matching method to explore the nodes reidentification in anonymous social graphs. The simulation results on two social network datasets show that the attack is feasible in the nodes reidentification in anonymous graphs including the simply anonymous graph, randomized graph andk-isomorphism graph.

Sign in / Sign up

Export Citation Format

Share Document