scholarly journals Going beyond accuracy: estimating homophily in social networks using predictions

2020 ◽  
Author(s):  
George Berry ◽  
Antonio Sirianni ◽  
Ingmar Weber ◽  
Jisun An ◽  
Michael MACY
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Prediction Models ◽  
Online Social Network ◽  
Classification Performance ◽  
Estimation Accuracy ◽  
Online Networks ◽  
Social Network Data ◽  
Relational Properties ◽  
Node Level

In online social networks, it is common to use predictions of node categories to estimate measures of homophily and other relational properties. However, online social network data often lacks basic demographic information about the nodes. Researchers must rely on predicted node attributes to estimate measures of homophily, but little is known about the validity of these measures. We show that estimating homophily in a network can be viewed as a dyadic prediction problem, and that homophily estimates are unbiased when dyad-level residuals sum to zero in the network. Node-level prediction models, such as the use of names to classify ethnicity or gender, do not generally have this property and can introduce large biases into homophily estimates. Bias occurs due to error autocorrelation along dyads. Importantly, node-level classification performance is not a reliable indicator of estimation accuracy for homophily. We compare estimation strategies that make predictions at the node and dyad levels, evaluating performance in different settings. We propose a novel “ego-alter” modeling approach that outperforms standard node and dyad classification strategies. While this paper focuses on homophily, results generalize to other relational measures which aggregate predictions along the dyads in a network. We conclude with suggestions for research designs to study homophily in online networks. Code for this paper is available at https://github.com/georgeberry/autocorr.

Exploring the Properties of Online Social Network Data and Their Implications for Consumer Social Data Analytics

2014 ◽  
pp. 210-230
Author(s):  
Yamen Koubaa
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Consumer Behavior ◽  
Online Social Networks ◽  
Data Analytics ◽  
Online Social Network ◽  
Network Data ◽  
Social Data ◽  
Social Network Data ◽  
Consumer Data

The prediction of consumer behavior is largely based on the analysis of consumer data using statistics as a tool for prediction. Thanks to online social networks, large quantities of heterogeneous consumer data are now available at competitive costs. Though they have much in common with conventional data, online social network datasets display several different properties. The exploration of these unique properties is indispensable to insuring the accuracy of predictions and data analytics. This chapter presents online social data, discusses seven properties of online social network data, suggests some analysis tools, and draws implications regarding the use of social data analytics.

scholarly journals How migrants manifest their transnational identity through online social networks: comparative findings from a case of Koreans in Germany

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Sunyoung Park ◽  
Lasse Gerrits
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Online Social Networks ◽  
Online Social Network ◽  
Point Of View ◽  
Comparative Case Study ◽  
Transnational Identity ◽  
Transnational Identities ◽  
Web 3.0 ◽  
Situational Contexts

AbstractAlthough migration has long been an imperative topic in social sciences, there are still needs of study on migrants’ unique and dynamic transnational identity, which heavily influences the social integration in the host society. In Online Social Network (OSN), where the contemporary migrants actively communicate and share their stories the most, different challenges against migrants’ belonging and identity and how they cope or reconcile may evidently exist. This paper aims to scrutinise how migrants are manifesting their belonging and identity via different technological types of online social networks, to understand the relations between online social networks and migrants’ multi-faceted transnational identity. The research introduces a comparative case study on an online social movement led by Koreans in Germany via their online communities, triggered by a German TV advertisement considered as stereotyping East Asians given by white supremacy’s point of view. Starting with virtual ethnography on three OSNs representing each of internet generations (Web 1.0 ~ Web 3.0), two-step Qualitative Data Analysis is carried out to examine how Korean migrants manifest their belonging and identity via their views on “who we are” and “who are others”. The analysis reveals how Korean migrants’ transnational identities differ by their expectation on the audience and the members in each online social network, which indicates that the distinctive features of the online platform may encourage or discourage them in shaping transnational identity as a group identity. The paper concludes with the two main emphases: first, current OSNs comprising different generational technologies play a significant role in understanding the migrants’ dynamic social values, and particularly, transnational identities. Second, the dynamics of migrants’ transnational identity engages diverse social and situational contexts. (keywords: transnational identity, migrants’ online social networks, stereotyping migrants, technological evolution of online social network).

Reducing Cumulative Errors of Incremental CP Decomposition in Dynamic Online Social Networks

2021 ◽  
Vol 15 (3) ◽  
pp. 1-33
Author(s):  
Jingjing Wang ◽  
Wenjun Jiang ◽  
Kenli Li ◽  
Keqin Li
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Prediction Error ◽  
High Efficiency ◽  
Optimization Problems ◽  
Online Social Network ◽  
Reconstruction Error ◽  
Incremental Updating ◽  
Cp Decomposition ◽  
Error Accumulation

CANDECOMP/PARAFAC (CP) decomposition is widely used in various online social network (OSN) applications. However, it is inefficient when dealing with massive and incremental data. Some incremental CP decomposition (ICP) methods have been proposed to improve the efficiency and process evolving data, by updating decomposition results according to the newly added data. The ICP methods are efficient, but inaccurate because of serious error accumulation caused by approximation in the incremental updating. To promote the wide use of ICP, we strive to reduce its cumulative errors while keeping high efficiency. We first differentiate all possible errors in ICP into two types: the cumulative reconstruction error and the prediction error. Next, we formulate two optimization problems for reducing the two errors. Then, we propose several restarting strategies to address the two problems. Finally, we test the effectiveness in three typical dynamic OSN applications. To the best of our knowledge, this is the first work on reducing the cumulative errors of the ICP methods in dynamic OSNs.

Quantifying Virality of Information in Online Social Networks

2012 ◽  
Vol 4 (1) ◽  
pp. 32-45 ◽  
Author(s):  
Abhishek Vaish ◽  
Rajiv Krishna G. ◽  
Akshay Saxena ◽  
Dharmaprakash M. ◽  
Utkarsh Goel
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Online Social Networks ◽  
Online Social Network ◽  
Critical Factors ◽  
Asset Valuation ◽  
Valuation Technique ◽  
Information Item ◽  
Viral Nature ◽  
Over Time

The aim of this research is to propose a model through which the viral nature of an information item in an online social network can be quantified. Further, the authors propose an alternate technique for information asset valuation by accommodating virality in it which not only complements the existing valuation system, but also improves the accuracy of the results. They use a popularly available YouTube dataset to collect attributes and measure critical factors such as share-count, appreciation, user rating, controversiality, and comment rate. These variables are used with a proposed formula to obtain viral index of each video on a given date. The authors then identify a conventional and a hybrid asset valuation technique to demonstrate how virality can fit in to provide accurate results.The research demonstrates the dependency of virality on critical social network factors. With the help of a second dataset acquired, the authors determine the pattern virality of an information item takes over time.

scholarly journals Defining Inspection Techniques for Detecting Privacy Problems in Online Social Networks

2019 ◽  
Vol 10 ◽  
pp. 35
Author(s):  
Andrey  Rodrigues ◽  
Natasha  M. C. Valentim ◽  
Eduardo  Feitosa
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Empirical Study ◽  
Qualitative Analysis ◽  
Online Social Networks ◽  
Online Social Network ◽  
Effective Alternative ◽  
Daily Lives ◽  
Study Participants ◽  
Inspection Techniques

In the last few years, Online Social Networks (OSN) have experienced growth in the number of users, becoming an increasingly embedded part of people’s daily lives. Privacy expectations of OSNs are higher as more members start realizing potential privacy problems they face by interacting with these systems. Inspection methods can be an effective alternative for addressing privacy problems because they detect possible defects that could be causing the system to behave in an undesirable way. Therefore, we proposed a set of privacy inspection techniques called PIT-OSN (Privacy Inspection Techniques for Online Social Network). This paper presents the description and evolution of PIT-OSN through the results of a preliminary empirical study. We discuss the quantitative and qualitative results and their impact on improving the techniques. Results indicate that our techniques assist non-expert inspectors uncover privacy problems effectively, and are considered easy to use and useful by the study participants. Finally, the qualitative analysis helped us improve some technique steps that might be unclear.

scholarly journals DeepOSN: Bringing deep learning as malicious detection scheme in online social network

2020 ◽  
Vol 9 (1) ◽  
pp. 146
Author(s):  
Putra Wanda ◽  
Marselina Endah Hiswati ◽  
Huang J. Jie
Keyword(s):  
Social Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Online Social Networks ◽  
Link Prediction ◽  
Online Social Network ◽  
Detection Scheme ◽  
Malicious Activity ◽  
Manual Analysis ◽  
Learning Techniques

Manual analysis for malicious prediction in Online Social Networks (OSN) is time-consuming and costly. With growing users within the environment, it becomes one of the main obstacles. Deep learning is growing algorithm that gains a big success in computer vision problem. Currently, many research communities have proposed deep learning techniques to automate security tasks, including anomalous detection, malicious link prediction, and intrusion detection in OSN. Notably, this article describes how deep learning makes the OSN security technique more intelligent for detecting malicious activity by establishing a classifier model.

Social Identities, Group Formation, and the Analysis of Online Communities

2010 ◽  
pp. 1346-1361 ◽  
Author(s):  
Jillianne R. Code ◽  
Nicholas E. Zaparyniuk
Keyword(s):  
Social Networks ◽  
Social Identity ◽  
Online Communities ◽  
Collective Identity ◽  
Online Social Networks ◽  
Online Social Network ◽  
Group Formation ◽  
Social Identities ◽  
New Members ◽  
The Individual

Central to research in social psychology is the means in which communities form, attract new members, and develop over time. Research has found that the relative anonymity of Internet communication encourages self-expression and facilitates the formation of relationships based on shared values and beliefs. Self-expression in online social networks enables identity experimentation and development. As identities are fluid, situationally contingent, and are the perpetual subject and object of negotiation within the individual, the presented and perceived identity of the individual may not match reality. In this chapter, the authors consider the psychological challenges unique to understanding the dynamics of social identity formation and strategic interaction in online social networks. The psychological development of social identities in online social network interaction is discussed, highlighting how collective identity and self-categorization associates social identity to online group formation. The overall aim of this chapter is to explore how social identity affects the formation and development of online communities, how to analyze the development of these communities, and the implications such social networks have within education.

Building Online Social Networks to Engage Female Students in Information Systems

2015 ◽  
Vol 10 (4) ◽  
pp. 33-51
Author(s):  
Jaymeen R. Shah ◽  
Hsun-Ming Lee
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Information Systems ◽  
Online Social Networks ◽  
Social Networking Sites ◽  
Role Models ◽  
Online Social Network ◽  
Research Process ◽  
Female Students ◽  
The Social

During the next decade, enrollment growth in Information Systems (IS) related majors is unlikely to meet the predicted demand for qualified IS graduates. Gender imbalance in the IS related program makes the situation worse as enrollment and retention of women in the IS major has been proportionately low compared to male. In recent years, majority of high school and college students have integrated social networking sites in their daily life and habitually use these sites. Providing female students access to role models via an online social network may enhance their motivation to continue as an IS major and pursue a career in IS field. For this study, the authors follow the action research process – exploration of information systems development. In particular, a Facebook application was developed to build the social network connecting role models and students. Using the application, a basic framework is tested based on the gender of participants. The results suggest that it is necessary to have adequate number of role models accessible to students as female role-models tend to select fewer students to develop relationships with a preference for female students. Female students likely prefer composite role models from a variety of sources. This pilot study yields valuable lessons to provide informal learning fostered by role modeling via online social networks. The Facebook application may be further expanded to enhance female students' interests in IS related careers.

scholarly journals Awesome women and bad feminists: the role of online social networks and peer support for feminist practice in academia

2019 ◽  
Vol 27 (3) ◽  
pp. 415-435
Author(s):  
Hannah Bayfield ◽  
Laura Colebrooke ◽  
Hannah Pitt ◽  
Rhiannon Pugh ◽  
Natalia Stutter
Keyword(s):  
Higher Education ◽  
Social Networks ◽  
Peer Support ◽  
Online Social Networks ◽  
Online Collaboration ◽  
Online Networks ◽  
Feminist Practice ◽  
Digital Spaces

In her book, ‘Bad Feminist’, Roxane Gay claims this label shamelessly, embracing the contradictory aspects of enacting feminist practice while fundamentally being ‘flawed human[s]’. This article tells a story inspired by and enacting Roxane Gay’s approach in academia, written by five cis-gendered women geographers. It is the story of a proactive, everyday feminist initiative to survive as women in an academic precariat fuelled by globalised, neoliberalised higher education. We reflect on what it means to be (bad) feminists in that context, and how we respond as academics. We share experiences of an online space used to support one another through post-doctoral life, a simple message thread, which has established an important role in our development as academics and feminists. This article, written through online collaboration, mirrors and enacts processes fundamental to our online network, demonstrating the significance and potential of safe digital spaces for peer support. Excerpts from the chat reflect critically on struggles and solutions we have co-developed. Through this, we celebrate and validate a strategy we know that we and others like us find invaluable for our wellbeing and survival. Finally, we reflect on the inherent limitations of exclusive online networks as tools for feminist resistance.

Social Identities, Group Formation, and the Analysis of Online Communities

2010 ◽  
pp. 86-101 ◽  
Author(s):  
Jillianne R. Code ◽  
Nicholas E. Zaparyniuk
Keyword(s):  
Social Networks ◽  
Social Identity ◽  
Online Communities ◽  
Collective Identity ◽  
Online Social Networks ◽  
Online Social Network ◽  
Group Formation ◽  
Social Identities ◽  
New Members ◽  
The Individual

Central to research in social psychology is the means in which communities form, attract new members, and develop over time. Research has found that the relative anonymity of Internet communication encourages self-expression and facilitates the formation of relationships based on shared values and beliefs. Self-expression in online social networks enables identity experimentation and development. As identities are fluid, situationally contingent, and are the perpetual subject and object of negotiation within the individual, the presented and perceived identity of the individual may not match reality. In this chapter, the authors consider the psychological challenges unique to understanding the dynamics of social identity formation and strategic interaction in online social networks. The psychological development of social identities in online social network interaction is discussed, highlighting how collective identity and self-categorization associates social identity to online group formation. The overall aim of this chapter is to explore how social identity affects the formation and development of online communities, how to analyze the development of these communities, and the implications such social networks have within education.

Sign in / Sign up

Export Citation Format

Share Document