Fine-Grained Feature-Based Social Influence Evaluation in Online Social Networks

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.

Download Full-text

Incremental Group-Level Popularity Prediction in Online Social Networks

ACM Transactions on Internet Technology ◽

10.1145/3461839 ◽

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.

Download Full-text

Understanding Weight Change Behaviors through Online Social Networks

International Journal of Computational Models and Algorithms in Medicine ◽

10.4018/jcmam.2011070104 ◽

2011 ◽

Vol 2 (3) ◽

pp. 46-69 ◽

Cited By ~ 2

Author(s):

Xiaoxiao Ma ◽

Guanling Chen ◽

Juntao Xiao

Keyword(s):

Social Networks ◽

Social Network ◽

Social Influence ◽

Empirical Analysis ◽

Real World ◽

Weight Change ◽

Online Social Networks ◽

Community Support ◽

Propagation Distance ◽

Weight Changes

Online Social Networks (OSNs) provide a good way to make connections with people with similar interests and goals. In particular, health-centered OSNs are emerging to provide knowledge and support for those interested in managing their own health. This paper provides an empirical analysis of a health OSN, which allows its users to record their foods and exercises, track their diet progress toward weight-change goals, and socialize and group with each other for community support. Based on about five month data collected from more than 107,000 users, the authors studied their weigh-in behaviors and tracked their weight-change progress. The authors found that the users’ weight changes correlated positively with the number of weigh-ins, the number of their friends, and their friends’ weight-change performance. The authors also show that the users’ weight changes have rippling effects in the OSN due to social influence. The strength of such online influence and its propagation distance appear to be greater than those in a real-world social network.

Download Full-text

Routing and Scheduling of Social Influence Diffusion in Online Social Networks

2016 IEEE 36th International Conference on Distributed Computing Systems (ICDCS) ◽

10.1109/icdcs.2016.45 ◽

2016 ◽

Cited By ~ 2

Author(s):

Hui-Ju Hung ◽

De-Nian Yang ◽

Wang-Chien Lee

Keyword(s):

Social Networks ◽

Social Influence ◽

Online Social Networks ◽

Routing And Scheduling ◽

Influence Diffusion

Download Full-text

Efficient Estimation of Network Games of Incomplete Information: Application to Large Online Social Networks

Management Science ◽

10.1287/mnsc.2020.3885 ◽

2021 ◽

Author(s):

Xi Chen ◽

Ralf van der Lans ◽

Michael Trusov

Keyword(s):

Social Networks ◽

Social Influence ◽

Incomplete Information ◽

Community Detection ◽

Online Social Networks ◽

Choice Model ◽

Real Life ◽

Efficient Estimation ◽

Data Set ◽

Detection Algorithms

This paper presents a structural discrete choice model with social influence for large-scale social networks. The model is based on an incomplete information game and permits individual-specific parameters of consumers. It is challenging to apply this type of models to real-life scenarios for two reasons: (1) The computation of the Bayesian–Nash equilibrium is highly demanding; and (2) the identification of social influence requires the use of excluded variables that are oftentimes unavailable. To address these challenges, we derive the unique equilibrium conditions of the game, which allow us to employ a stochastic Bayesian estimation procedure that is scalable to large social networks. To facilitate the identification, we utilize community-detection algorithms to divide the network into different groups that, in turn, can be used to construct excluded variables. We validate the proposed structural model with the login decisions of more than 25,000 users of an online social game. Importantly, this data set also contains promotions that were exogenously determined and targeted to only a subgroup of consumers. This information allows us to perform exogeneity tests to validate our identification strategy using community-detection algorithms. Finally, we demonstrate the managerial usefulness of the proposed methodology for improving the strategies of targeting influential consumers in large social networks. This paper was accepted by Matthew Shum, marketing.

Download Full-text

Social Networks in which Users are not Small Circles

Informing Science The International Journal of an Emerging Transdiscipline ◽

10.28945/2196 ◽

2015 ◽

Vol 18 ◽

pp. 205-224 ◽

Cited By ~ 1

Author(s):

Sabah Al-Fedaghi ◽

Heba AlMeshari

Keyword(s):

Social Networks ◽

Online Social Networks ◽

Distribution Systems ◽

User Behavior ◽

Clustering Coefficient ◽

Graph Representations ◽

Small Circle ◽

Fine Grained ◽

Social Network Structure ◽

Placement Policies

Understanding of social network structure and user behavior has important implications for site design, applications (e.g., ad placement policies), accurate modeling for social studies, and design of next-generation infrastructure and content distribution systems. Currently, characterizations of social networks have been dominated by topological studies in which graph representations are analyzed in terms of connectivity using techniques such as degree distribution, diameter, average degree, clustering coefficient, average path length, and cycles. The problem is that these parameters are not completely satisfactory in the sense that they cannot account for individual events and have only limited use, since one can produce a set of synthetic graphs that have the exact same metrics or statistics but exhibit fundamentally different connectivity structures. In such an approach, a node drawn as a small circle represents an individual. A small circle reflects a black box model in which the interior of the node is blocked from view. This paper focuses on the node level by considering the structural interiority of a node to provide a more fine-grained understanding of social networks. Node interiors are modeled by use of six generic stages: creation, release, transfer, arrival, acceptance, and processing of the artifacts that flow among and within nodes. The resulting description portrays nodes as comprising mostly creators (e.g., of data), receivers/senders (e.g., bus boys), and processors (re-formatters). Two sample online social networks are analyzed according to these features of nodes. This examination points to the viability of the representational method for characterization of social networks.

Download Full-text

Cross-site Prediction on Social Influence for Cold-start Users in Online Social Networks

ACM Transactions on the Web ◽

10.1145/3409108 ◽

2021 ◽

Vol 15 (2) ◽

pp. 1-23

Author(s):

Qingyuan Gong ◽

Yang Chen ◽

Xinlei He ◽

Yu Xiao ◽

Pan Hui ◽

...

Keyword(s):

Social Networks ◽

Social Influence ◽

Online Social Networks ◽

Cold Start ◽

Learning Technologies ◽

Viral Marketing ◽

Supervised Machine Learning ◽

Activity Data ◽

Public Data ◽

Influential Users

Online social networks (OSNs) have become a commodity in our daily life. As an important concept in sociology and viral marketing, the study of social influence has received a lot of attentions in academia. Most of the existing proposals work well on dominant OSNs, such as Twitter, since these sites are mature and many users have generated a large amount of data for the calculation of social influence. Unfortunately, cold-start users on emerging OSNs generate much less activity data, which makes it challenging to identify potential influential users among them. In this work, we propose a practical solution to predict whether a cold-start user will become an influential user on an emerging OSN, by opportunistically leveraging the user’s information on dominant OSNs. A supervised machine learning-based approach is adopted, transferring the knowledge of both the descriptive information and dynamic activities on dominant OSNs. Descriptive features are extracted from the public data on a user’s homepage. In particular, to extract useful information from the fine-grained dynamic activities that cannot be represented by the statistical indices, we use deep learning technologies to deal with the sequential activity data. Using the real data of millions of users collected from Twitter (a dominant OSN) and Medium (an emerging OSN), we evaluate the performance of our proposed framework to predict prospective influential users. Our system achieves a high prediction performance based on different social influence definitions.

Download Full-text