CSD: A multi-user similarity metric for community recommendation in online social networks

Xiao, Han; Wang, Leye; Farahbakhsh, Reza; Cuevas, Antonio; Cuevas, Rubén; Crespi, Noël; He, Lina

doi:10.1016/j.eswa.2016.01.003

Cited by 42 publications

(21 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The parameters for modeling individual diffusion preference α, β, ρ Dirichlet priors Table 2: Notations work to our three example applications, including community ranking, community diffusion and community visualization. Firstly, for community ranking, most of existing studies [14,7] rank communities based on users' interests on them, i.e., to find the favourite communities for users. Moreover, the communities to be ranked are often already predefined over the networks.…”

Section: Related Workmentioning

confidence: 99%

“…This quality criterion will later guide us to estimate the profiles accurately. It is also a key to differentiating us from other work-some prior attempt simply aggregates user information to output community properties (mostly internal ones) [14], but it does not require such properties to best explain the observations of user behaviors as generated by the communities through them.…”

Section: Introductionmentioning

confidence: 99%

“…Since we have known what content each community is interested in and how it diffuses that content with others, we can rank the communities. Profile-driven community ranking is different from the traditional community recommendation, which often relies on only "community-X" properties and is unaware of diffusion [7,14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

From community detection to community profiling

et al. 2017

View full text Add to dashboard Cite

Most existing community-related studies focus on detection, which aim to find the community membership for each user from user friendship links. However, membership alone, without a complete profile of what a community is and how it interacts with other communities, has limited applications. This motivates us to consider systematically profiling the communities and thereby developing useful community-level applications. In this paper, we for the first time formalize the concept of community profiling. With rich user information on the network, such as user published content and user diffusion links, we characterize a community in terms of both its internal content profile and external diffusion profile. The difficulty of community profiling is often underestimated. We novelly identify three unique challenges and propose a joint Community Profiling and Detection (CPD) model to address them accordingly. We also contribute a scalable inference algorithm, which scales linearly with the data size and it is easily parallelizable. We evaluate CPD on large-scale real-world data sets, and show that it is significantly better than the state-of-the-art baselines in various tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

From community detection to community profiling

et al. 2017

View full text Add to dashboard Cite

show abstract

“…For example, Orkut maintains more than 100 million communities every day. Due to the large number of social communities and the similar properties of social members within each community, community has become a basic components in OSNs . In urban vehicular networking environment, subject to the limited wireless network sources in UVSNs, collaboration between social communities is pivotal to maximize the benefit of urban vehicular social networking .…”

Section: Introductionmentioning

confidence: 99%

“…Due to the large number of social communities and the similar properties of social members within each community, community has become a basic components in OSNs. [3][4][5] In urban vehicular networking environment, subject to the limited wireless network sources in UVSNs, collaboration between social communities is pivotal to maximize the benefit of urban vehicular social networking. 6,7 As one of the significant collaboration patterns, social recommendation between communities plays a more and more significant role in urban vehicular social networks than in any other kind of social network.…”

Section: Introductionmentioning

confidence: 99%

Social recommendation between urban vehicular social communities

Liu

Wang

Sun

et al. 2018

Int J Communication

View full text Add to dashboard Cite

Summary In recent years, social recommendation between communities plays a more and more significant role in urban vehicular social networks. It has become a hot research topic due to its advantage in enhancing the efficiency of information sharing and transmission in urban vehicular social networks. This paper focuses on social recommendation between communities where achieving the optimal configuration of social recommendation is NP‐hard. We proposed an algorithm for the near optimal configuration of social recommendation between urban vehicular social communities (ANOCSR) to make this NP‐hard problem polynomially solvable based on a modified Steiner minimal tree method. Moreover, with the help of the ANOCSR, we propose another algorithm to achieve the optimal configuration of social recommendation between urban vehicular social communities subject to a global external trust value constraint (AOCSRC). We demonstrate that our algorithms are more efficient and effective than existing algorithms through extensive experiments and detailed theoretical analyses.

show abstract

Encyclopedia of Social Network Analysis and Mining

Alhajj¹,

Rokne²

2016

View full text Add to dashboard Cite

This entry discusses the problem of describing some communities identified in a complex network of interest, in a way allowing to interpret them. We suppose the community structure has already been detected through one of the many methods proposed in the literature. The question is then to know how to extract valuable information from this first result, in order to allow human interpretation. This requires subsequent processing, which we describe in the rest of this entry.

show abstract

CSD: A multi-user similarity metric for community recommendation in online social networks

Cited by 42 publications

References 27 publications

From community detection to community profiling

From community detection to community profiling

Social recommendation between urban vehicular social communities

Encyclopedia of Social Network Analysis and Mining

Contact Info

Product

Resources

About