scholarly journals HetInf: Social Influence Prediction With Heterogeneous Graph Neural Network

2022 ◽  
Vol 9 ◽  
Author(s):  
Liqun Gao ◽  
Haiyang Wang ◽  
Zhouran Zhang ◽  
Hongwu Zhuang ◽  
Bin Zhou
Keyword(s):  
Neural Network ◽  
Social Network ◽  
Social Influence ◽  
User Behavior ◽  
Online Advertising ◽  
Live Streaming ◽  
Network Applications ◽  
Key Factor ◽  
Study Designs ◽  
The Impact

With the continuous enrichment of social network applications, such as TikTok, Weibo, Twitter, and others, social media have become an indispensable part of our lives. Web users can participate in their favorite events or pay attention to people they like. The “heterogeneous” influence between events and users can be effectively modeled, and users’ potential future behaviors can be predicted, so as to facilitate applications such as recommendations and online advertising. For example, a user’s favorite live streaming host (user) recommends certain products (event), can we predict whether the user will buy these products in the future? The majority of studies are based on a homogeneous graph neural network to model the influence between users. However, these studies ignore the impact of events on users in reality. For instance, when users purchase commodities through live streaming channels, in addition to the factors of the host, the commodity is also a key factor that influences the behavior of users. This study designs an influence prediction model based on a heterogeneous neural network HetInf. Specifically, we first constructed the heterogeneous social influence network according to the relationship between event nodes and user nodes, then sampled the user heterogeneous subgraph for each user, extracted the relevant node features, and finally predicted the probability of user behavior through the heterogeneous neural network model. We conducted comprehensive experiments on two large social network datasets. Furthermore, the experimental results show that HetInf is significantly superior to the previous homogeneous neural network methods.

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.

Why do People Continue to Play Social Network Game (SNG)?

2013 ◽  
Vol 5 (4) ◽  
pp. 22-35 ◽  
Author(s):  
Tzu-Hong Lin ◽  
Hsi-Peng Lu ◽  
Huei-Hsia Hsu ◽  
San-San Hsing ◽  
Tai-Li Ho
Keyword(s):  
Social Network ◽  
Word Of Mouth ◽  
Social Perspective ◽  
Network Game ◽  
Determining Factors ◽  
Key Factor ◽  
Continuous Use ◽  
The Impact ◽  
Loyal Customers

This study proposes a model constructed by affection perspective (PA theory) and social perspective to examine the determining factors of social network game (SNG) players' intentions on word-of-mouth and continue. Total 276 subjects were conducted to test this model. The results demonstrate that interstate of arousal leads people to a higher level of continuing to use on SNG. Moreover, word-of-mouth had significant impact on continue to use, which showed that the impact of the dimension of continue to use on the word-of-mouth. It was found that sharing was a key factor on determining a player's intentions to word-of-mouth and continuous use on social network game. Through the increasing stickiness and word-of-mouth for SNG, the games providers could create the higher value from loyal customers. This paper contributes to an insight of the effects of players' intentions on word-of-mouth and continuance to use on SNG.

Social influence or personal attitudes?

Kybernetes ◽  
2019 ◽  
Vol 48 (3) ◽  
pp. 424-437 ◽  
Author(s):  
Xue Yang
Keyword(s):  
Social Network ◽  
Social Identity ◽  
Social Influence ◽  
Online Survey ◽  
Continuance Intention ◽  
Data Set ◽  
Content Type ◽  
Social Influence Theory ◽  
Personal Attitudes ◽  
The Impact

PurposeThis study aimed to examine the impact of social influence and personal attitudes on users’ continuance intention. Based on social influence theory, this study developed a theoretical model to explore what factors can influence users’ social network sites continuance intention.Design/methodology/approachTo validate the research model, the authors used an online survey instrument to gather data. Hypotheses were tested using partial least squares modeling.FindingsUsing a data set including 229 WeChat users in China, the authors found that the influence of subjective norms and group norms on continuance intention is insignificant. Moreover, social identity and personal attitudes were proved to be significant predictors of continuance intention. Specifically, gender played a moderating role in the relationship between social identity and continuance intention. In addition, gender moderated the effect of personal attitudes on continuance intention as well.Originality/valueThis study provided insights into how social influence affects users’ continuance intention. Moreover, this study concentrated on the different impact of social influence and personal attitudes on users’ continuance intention. Specifically, the authors explored gender differences in users’ continuance intention. The results extend the knowledge about the differences of males versus females in using social network sits.

scholarly journals The Impact of Community Structure on the Convergence Time of Opinion Dynamics

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
An Lu ◽  
Chunhua Sun ◽  
Yezheng Liu
Keyword(s):  
Community Structure ◽  
Social Network ◽  
Social Influence ◽  
Opinion Dynamics ◽  
Matrix Analysis ◽  
Convergence Time ◽  
Influence Matrix ◽  
The Social ◽  
The Impact ◽  
Second Largest Eigenvalue

We analyze the convergence time of opinion dynamics in a social network with community structure. Using matrix analysis, we prove that the convergence time is determined by the second largest eigenvalue modulus. This modulus is close to 1 if the social influence matrix is nearly uncoupled. Furthermore, we discuss and analyze the factors of community structure affecting the convergence time.

scholarly journals The impact of using Mobile Social Network Applications on Students’ Social-Life

2018 ◽  
Vol 11 (2) ◽  
pp. 1-14 ◽  
Author(s):  
Ahmed Yousif Abdelraheem ◽  
◽  
Abdelrahman Mohammed Ahmed ◽  
Keyword(s):  
Social Network ◽  
Social Life ◽  
Mobile Social Network ◽  
Network Applications ◽  
The Impact

scholarly journals Systematic Review on Mentalization as Key Factor in Psychotherapy

2021 ◽  
Vol 18 (17) ◽  
pp. 9161
Author(s):  
Jonas Lüdemann ◽  
Sven Rabung ◽  
Sylke Andreas
Keyword(s):  
Systematic Review ◽  
Psychotherapy Research ◽  
Exact Role ◽  
Key Factor ◽  
Electronic Database Search ◽  
Study Designs ◽  
The Impact ◽  
Present Systematic Review ◽  
Final Synthesis

Background: Mentalization processes seem to be of high relevance for social learning and seem important in all psychotherapies. The exact role of mentalization processes in psychotherapy is still unknown. The aim of the present systematic review is to investigate whether mentalization is related to the therapeutic outcome and, if so, whether it has a moderating, mediative, or predictive function. Method: A systematic review with an electronic database search was conducted. A total of 2567 records were identified, and 10 studies were included in the final synthesis. Results: Psychotherapy research is still in an initial phase of examining and understanding the impact of mentalization on psychotherapy outcome. The small number of studies and the executed study designs and statistical analyses indicate the possible role that mentalization has in psychotherapy. Conclusion: Generally, strongly elaborated study designs are needed to identify the role of mentalization in psychotherapy. Mentalization seems to be differently represented in differential treatment approaches. Nevertheless, it should be noted that the patient’s mentalizing capacity seems to be relevant to the psychotherapy process. Psychotherapies should be adapted to this.

scholarly journals A model for art communication and development under the influence of social network

2020 ◽  
Vol 32 ◽  
Author(s):  
Dongsheng ZHANG ◽  
Daodong SUN
Keyword(s):  
Social Network ◽  
High Efficiency ◽  
User Behavior ◽  
Development Model ◽  
Dynamics Model ◽  
Seir Model ◽  
New Model ◽  
Epidemic Dynamics ◽  
Node Classification ◽  
The Impact

Abstract Improving the value of art information and user behavior factors can boost the effect of art communication and development. This paper proposes a social network based on the s-seir (Single SEIR) art communication and development model, a new model developed based on the SEIR (Susceptible, Exposed, Infectious, Recovered) classical epidemic dynamics model. In addition, we present the concept and characteristics of art communication, summarize the rules of node classification and art information evolution, and design an interpretative s-seir model considering the value of art information and user behavior factors. The experimental results show that the model can clearly analyze the impact of art value and user behavior on the dissemination and development of art information, and has the advantages of high efficiency and accuracy.

Sign in / Sign up

Export Citation Format

Share Document