Difference between revisions of "Mrinmaya et. al. WWW'12"
| Line 25: | Line 25: | ||
== Summary == | == Summary == | ||
In this paper, the authors study the problem of communities detection in social networks. They employ the probabilistic approach and propose a generative model that describes how users' messages and interactions are generated from the hidden membership of each user. The general model, or ``full model" as called by the author, has the generative process as follows. | In this paper, the authors study the problem of communities detection in social networks. They employ the probabilistic approach and propose a generative model that describes how users' messages and interactions are generated from the hidden membership of each user. The general model, or ``full model" as called by the author, has the generative process as follows. | ||
| − | *For each of the topics, <math>1 \leq z \leq Z</math>, sample a <math>V</math> dimensional multinomial | + | *For each of the topics, <math>1 \leq z \leq Z</math>, sample topic <math>z</math> as a <math>V</math> dimensional multinomial distribution over words <math>\vec{\lambda_z}\sim Dir_V (\delta) </math> |
| − | + | *For each of the communities, <math>1\leq c \leq C</math> sample social type interaction <math>c</math> as a<math>X</math> dimensional multinomial distribution over type of interactions | |
| − | *For each of the communities, 1 | + | <math>\phi_c \sim Dir_X(\beta)</math> |
| − | X dimensional | + | *For each of the communities, <math>1\leq c \leq C</math> sample social type interaction recipient <math>c</math> as a<math>U</math> dimensional multinomial distribution over set of users <math>\xi_c \sim Dir_U(\epsilon)</math> |
| − | + | <math>\phi_c \sim Dir_X(\beta)</math> | |
| − | |||
| − | *For each of the communities, 1 | ||
| − | dimensional | ||
| − | |||
| − | |||
4. For the i | 4. For the i | ||
th | th | ||
Revision as of 12:28, 2 October 2012
This is a scientific paper authored by Mrinmaya Sachan, and appeared in WWW'12. Below is the paper summary written by Tuan Anh.
Citation
@inproceedings{Sachan:2012:UCI:2187836.2187882,
author = {Sachan, Mrinmaya and Contractor, Danish and Faruquie, Tanveer A. and Subramaniam, L. Venkata},
title = {Using content and interactions for discovering communities in social networks},
booktitle = {Proceedings of the 21st international conference on World Wide Web},
series = {WWW '12},
year = {2012},
isbn = {978-1-4503-1229-5},
location = {Lyon, France},
pages = {331--340},
numpages = {10},
url = {http://doi.acm.org/10.1145/2187836.2187882},
doi = {10.1145/2187836.2187882},
acmid = {2187882},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {community detection, probabilistic methods, social networks},
}
Online Version
Using Content and Interactions for Discovering Communities in Social Networks.
Summary
In this paper, the authors study the problem of communities detection in social networks. They employ the probabilistic approach and propose a generative model that describes how users' messages and interactions are generated from the hidden membership of each user. The general model, or ``full model" as called by the author, has the generative process as follows.
- For each of the topics, , sample topic as a dimensional multinomial distribution over words
- For each of the communities, sample social type interaction as a dimensional multinomial distribution over type of interactions
- For each of the communities, sample social type interaction recipient as a dimensional multinomial distribution over set of users
4. For the i th user ui, 1 � ui � U: (a) Sample a C dimensional multinomial, ~ �ui � DirC(�), representing the community proportions for that sender. (b) For each community c 2 C, sample a Z dimen- sional multinomial, ~�ui;c � DirZ(�), representing the topic proportions for community and sender. (c) For each post p (1 � p � Pi) generated by the sender ui: having Np words: i. Choose a community assignment cp � Mult( ~ �ui ) cp 2 [1 : C] for the post. ii. For each recipient slot i, 1 � i � Rp of the post p: A. Choose a recipient rp � Mult( ~ cp ) rpi 2 [1 : Rp] for the post.
Dicussion
Related papers
- Airoldi. et. al. Mixed Membership Stochastic Blockmodels. Journal of Machine Learning Research 9 (2008) 1981-2014
- Blei. et. al. Latent Dirichlet Allocation. Journal of Machine Learning Research 3 (2003) 993-1022
- Gregor Heinrich's note on Parameter estimation for text analysis
