Adding community and dynamic to topic models

Li, Daifeng; Ding, Ying; Shuai, Xin; Bollen, Johan; Tang, Jie; Chen, Shanshan; Zhu, Jihong; Rocha, Guilherme

doi:10.1016/j.joi.2011.11.004

Cited by 32 publications

(16 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This implies that community detection should consider both the topological and topical features of the networks. There are some initial efforts towards such direction: Zhou, Manavoglu, et al (2006)'s Community-User-Topic model; Li et al (2010)'s inference model of combining LDA and Girvan-Newman approach;and Li et al (2011)'s semi-supervised dynamic community topic model. These early efforts mainly extended LDA by modeling communities as a multinomial distribution over the networks of authors and their topics.…”

Section: Resultsmentioning

confidence: 99%

Community detection: Topological vs. topical

Ding

2011

Journal of Informetrics

Self Cite

106

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Community detection: Topological vs. topical

Ding

2011

Journal of Informetrics

Self Cite

106

View full text Add to dashboard Cite

“…Konu modelleri sosyal ağlar için yorumlanarak geliştirilmektedir. CUT [8], CART [9] ve CT [10] modelleri ortak ilgi alanlarına sahip ağ üyelerini gruplamak için kullanılmaktadır. Konu modelleri ağın topolojik yapısını göz ardı ettiğinden düşük modülerlik değeri üretmektedir.…”

Section: İlgi̇li̇ çAlişmalarunclassified

“…Topluluk tespitinde kullanılan diğer bir yaklaşım ise içerik analizi ile bireylerin ortak ilgi alanlarına göre gruplandırılmasıdır [8][9][10][11]. Sosyal ağları kullanan bireyler medya paylaşımları, ağ günlükleri ve e-postalar gibi farklı, anlamlı ve işlenebilir verileri paylaşmaktadırlar.…”

Section: Introductionunclassified

Community detection in social networks using content and link analysis

Kakisim

Soğukpınar

2015

2015 23nd Signal Processing and Communications Applications Conference (SIU)

View full text Add to dashboard Cite

Özetçe-Son zamanlarda sosyal ağlarda topluluk tanıma önemli bir problem olarak çalışılmaktadır. Birçok yöntem topluluk tanıma problemini ağın bağlantı yapısını analiz ederek çözmektedir. Bu durumda elde edilen topluluklar ağın yalnızca topolojik özelliğini yansıtmaktadır. Ağdaki kişiler arasında paylaşılan dokümanlar gözardı edilmektedir. Bu çalışmada, literatürde sıklıkla kullanılan ve bir hiyerarşik kümeleme algoritması olan modülerlik eniyileme algoritması ağdaki kişiler arasındaki benzerlikleri temel alarak yeniden yorumlanmıştır. Gerçek veri kümeleri ile çalışılarak elde edilen sonuçlar, önerilen algoritmanın daha başarılı olduğunu göstermektedir. Anahtar Kelimeler -topluluk tespiti; veri madenciliği; sosyal ağlar.Abstract-Recently, community detection in social networks is studied as a major problem. Most existing methods solve the problem of community detection using link structure of networks. In this case, communities only reflect the topological features of network. Documents of social members in network are ignored. In this paper, hierarchical modularity maximization algorithm that is frequently used in literature is modified using similarities between members. Experiments on real data sets, proposed algorithm can achieve a better performance.

show abstract

“…Similar to most of the existing community identification methods which focus on analyzing the topological structure of a social network, shared expertise among community members is mostly not considered. There are some recent works exploring semantically coherent communities [32][33][34].…”

Section: Related Workmentioning

confidence: 99%

The Author-Topic-Community model for author interest profiling and community discovery

Cheung

et al. 2014

Knowl Inf Syst

View full text Add to dashboard Cite

In this paper, we propose a generative model named the author-topic-community (ATC) model for representing a corpus of linked documents. The ATC model allows each author to be associated with a topic distribution and a community distribution as its model parameters. A learning algorithm based on variational inference is derived for the model parameter estimation where the two distributions are essentially reinforcing each other during the estimation. We compare the performance of the ATC model with two related generative models using first synthetic data sets and then real data sets, which include a research community data set, a blog data set, a news-sharing data set, and a microblogging data set. The empirical results obtained confirm that the proposed ATC model outperforms the existing models for tasks such as author interest profiling and author community discovery. We also demonstrate how the inferred ATC model can be used to characterize the roles of users/authors in online communities.

show abstract

Adding community and dynamic to topic models

Cited by 32 publications

References 22 publications

Community detection: Topological vs. topical

Community detection: Topological vs. topical

Community detection in social networks using content and link analysis

The Author-Topic-Community model for author interest profiling and community discovery

Contact Info

Product

Resources

About