Incremental Group-Level Popularity Prediction in Online Social Networks

2022 ◽  
Vol 22 (1) ◽  
pp. 1-26
Author(s):  
Jingjing Wang ◽  
Wenjun Jiang ◽  
Kenli Li ◽  
Guojun Wang ◽  
Keqin Li
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Low Cost ◽  
Tensor Decomposition ◽  
Group Level ◽  
Fine Grained ◽  
Cp Decomposition ◽  
Web Contents ◽  
Popularity Prediction ◽  
Novel Model

Predicting the popularity of web contents in online social networks is essential for many applications. However, existing works are usually under non-incremental settings. In other words, they have to rebuild models from scratch when new data occurs, which are inefficient in big data environments. It leads to an urgent need for incremental prediction, which can update previous results with new data and conduct prediction incrementally. Moreover, the promising direction of group-level popularity prediction has not been well treated, which explores fine-grained information while keeping a low cost. To this end, we identify the problem of incremental group-level popularity prediction, and propose a novel model IGPP to address it. We first predict the group-level popularity incrementally by exploiting the incremental CANDECOMP/PARAFCAC (CP) tensor decomposition algorithm. Then, to reduce the cumulative error by incremental prediction, we propose three strategies to restart the CP decomposition. To the best of our knowledge, this is the first work that identifies and solves the problem of incremental group-level popularity prediction. Extensive experimental results show significant improvements of the IGPP method over other works both in the prediction accuracy and the efficiency.

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.

scholarly journals Exploring how Homophily and Accessibility can Facilitate Polarization in Social Networks

2018 ◽  
Author(s):  
Cameron Taylor ◽  
Alexander V. Mantzaris ◽  
Ivan Garibay
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Low Cost ◽  
Voter Model ◽  
The Public ◽  
Pairwise Interactions ◽  
Online Social Media ◽  
Complete Networks ◽  
Social Media Platforms ◽  
The Public Sphere

Polarization in online social networks has gathered a significant amount of attention in the research community and in the public sphere due to stark disagreements with millions of participants in topics surrounding politics, climate, the economy and other areas where an agreement is required. There are multiple approaches to investigating the scenarios in which polarization occurs and given that polarization is not a new phenomenon but that its virality may be supported by the low cost and latency messaging offered by online social media platforms; an investigation into the intrinsic dynamics of online opinion evolution is presented for complete networks. Extending a model which utilizes the Binary Voter Model (BVM) to examine the effect of the degree of freedom for selecting contacts based upon homophily, simulations show that different opinions are reinforced for a period of time when users have a greater range of choice for association. The facility of discussion threads and groups formed upon common views further delays the rate in which a consensus can form between all members of the network. This can temporarily incubate members from interacting with those who can present an alternative opinion where a voter model would then proceed to produce a homogeneous opinion based upon pairwise interactions.

A NOVEL MODEL FOR RUMOR SPREADING ON SOCIAL NETWORKS WITH CONSIDERING THE INFLUENCE OF DISSENTING OPINIONS

2018 ◽  
Vol 21 (06n07) ◽  
pp. 1850011 ◽  
Author(s):  
AMIRHOSEIN BODAGHI ◽  
SAMA GOLIAEI
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Realistic Model ◽  
The Novel ◽  
Human Beings ◽  
Rumor Spreading ◽  
New Model ◽  
Sociological Factors ◽  
Novel Model ◽  
New Hypothesis

Rumor spreading is a good sample of spreading in which human beings are the main players in the spreading process. Therefore, in order to have a more realistic model of rumor spreading on online social networks, the influence of psycho-sociological factors particularly those which affect users’ reactions toward rumor/anti-rumor should be considered. To this aim, we present a new model that considers the influence of dissenting opinions on those users who have already believed in rumor/anti-rumor but have not spread the rumor/anti-rumor yet. We hypothesize that influence is a motive for the believers to spread their beliefs in rumor/anti-rumor. We derive the stochastic equations of the new model and evaluate it by using two real datasets of rumor spreading on Twitter. The evaluation results support the new hypothesis and show that the novel model which is relied on the new hypothesis is able to better represent rumor spreading.

Linking Multiple Identities in Online Social Networks Based on Co-Occurrence Analysis

2015 ◽  
Vol 713-715 ◽  
pp. 2257-2260
Author(s):  
Dong Liu ◽  
Quan Yuan Wu ◽  
Wei Hong Han
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Sliding Window ◽  
Multiple Identities ◽  
Fine Grained ◽  
Series Of Experiments ◽  
Colloquial Style

When tackling the problem of mining multiple fake identities which are controlled by the same individual in internet, traditional techniques used to analyze the posted comments using text-based methods. However, these texts are always in colloquial style which make the effect may not be as obvious as expected. In this paper a new multiple identities linking algorithm is proposed based on the fine-grained analysis of co-occurrence degree of user accounts using sliding window model. Finally, a series of experiments show the effectiveness of our proposed method.

scholarly journals Research Crowdfunding and Scholarly Communication: A Case Study of Three Campaigns

2018 ◽  
Author(s):  
Darren Chase ◽  
Dana Haugh ◽  
Victoria Pilato
Keyword(s):  
Social Networks ◽  
High Risk ◽  
Online Social Networks ◽  
Personal Narrative ◽  
Low Cost ◽  
Scholarly Communication ◽  
Narrative Style ◽  
Funded Research ◽  
Levels Of Support

Crowdfunding leverages the opportunities of online social networks to share ideas and connect individuals by seeking small donations from a large number of supporters in order to complete a project or develop a product. Research crowdfunding is emerging as a dynamic alternative or supplement to grant-funded research, particularly for low-cost research, researchers at institutions without strong traditions of grants-funded research, and high-risk or unconventional research with few or no sponsors. For some researchers, crowdfunding enables new and novel collaborations between researchers, entrepreneurs, artists, social and environmental activists, as well as facilitating unexpected uses and expressions of research.Through the lens of three qualitative crowdfunding campaign studies this article explores how crowdfunding conventions and platforms influence and impact the way research is used, communicated, shared, and in some cases performed. Successful crowdfunding relies on engagement and audience support -- higher levels of support include exclusive affordances, including opportunities to participate in events, acknowledgement in publications, and access to the researchers via online or in-person meetings. Crowdfunding platforms offer researchers the framework to appeal for support and communicate the details and progress of their research in a personal, narrative style, often utilizing video and social networks. This article will examine the new opportunities for communicating, sharing, and using research that crowdfunding facilitates through a case study of three crowdfunding campaigns.

scholarly journals Information Wars and Online Activism During the 2013/2014 Crisis in Ukraine: Examining the Social Structures of Pro- and Anti-Maidan Groups

2021 ◽  
Author(s):  
Anatoliy Gruzd ◽  
Ksenia Tsyganova
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Social Networking Site ◽  
Political Polarization ◽  
Group Level ◽  
Online Groups ◽  
Face To Face ◽  
Network Properties ◽  
Group Members ◽  
Online Activism

This article examines how online groups are formed and sustained during crisis periods, especially when political polarization in society is at its highest level. We focus on the use of Vkontakte (VK), a popular social networking site in Ukraine, to understand how it was used by Pro- and Anti-Maidan groups during the 2013/2014 crisis in Ukraine. In particular, we ask whether and to what extent the ideology (or other factors) of a particular group shapes its network structure. We find some support that online social networks are likely to represent local and potentially preexisting social networks, likely due to the dominance of reciprocal (and often close) relationships on VK and opportunities for group members to meet face-to-face during offline protests. We also identify a number of group-level indicators, such as degree centralization, modularity index and average engagement level, that could help to classify groups based on their network properties. Community researchers can start applying these group-level indicators to online communities outside VK; they can also learn from this article how to identify networks of spam and marketing accounts.

E-Marketing on Online Social Networks and Ethical Issues

2012 ◽  
Vol 2 (4) ◽  
pp. 1-14 ◽  
Author(s):  
Gajendra Sharma ◽  
Li Baoku
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Online Social Networks ◽  
Ethical Issues ◽  
Personal Information ◽  
Low Cost ◽  
Online Social Network ◽  
Communication Tool ◽  
Initial Product ◽  
Marketing Tool

Online social network is any electronic tool or application that provides information, allowing collaboration, interaction, and sharing information among users. The social network can be utilized as an e-marketing tool with low-cost and effective source of medium for marketers to identify market needs, customer experiences, competitive movements, and trends. The purpose of this paper is to study the significance of online social networks based on web 2.0 technologies on e-marketing promotion and potential challenging issue as well as needs of ethical standards. The paper adopts a broad literature review relating to e-marketing on online social networks and ethics. This study examines that the ethical issues such as acts, regulations and policies that govern privacy, the collection of personal information and the protection of a user’s identity are crucial when using social network for e-marketing and business promotion. As a communication tool the online social networks play a key role to reach initial product adopters and maintain interaction and collaboration with customers for market promotion.

Sign in / Sign up

Export Citation Format

Share Document