Detecting the emerging areas becomes interest by the fast development of social networks. As the information exchanged in social networks post include not only the text but also images, URLs and video therefore conventional-term-frequency-based approaches may not be appropriate in this context. Emergence of areas is focused by social aspects of these networks. To detect the emergence of new areas from the hundreds of users based on the responds in social network posts. A probability model is proposed for mentioning behavior of social networks by the number of mentions per post and the occurrence of users taking place in the mentions. The basic assumption is that a new emerging topic is something people feel like discussing, stating or forwarding the data further to their friends. In the proposed system the link anomaly model is combined with word based and text based approach
%0 Journal Article
%1 Ramya_2015
%A K.Ramya,
%A Rajakumari, S. Brintha
%A Nalini, Dr. T.
%D 2015
%I Auricle Technologies, Pvt., Ltd.
%J International Journal on Recent and Innovation Trends in Computing and Communication
%K Anomaly Burst Sequentially Social Topic coding detection discounted maximum-likelihood networks normalized
%N 3
%P 1338--1343
%R 10.17762/ijritcc2321-8169.150396
%T Detecting Emerging Areas in Social Streams
%U http://dx.doi.org/10.17762/ijritcc2321-8169.150396
%V 3
%X Detecting the emerging areas becomes interest by the fast development of social networks. As the information exchanged in social networks post include not only the text but also images, URLs and video therefore conventional-term-frequency-based approaches may not be appropriate in this context. Emergence of areas is focused by social aspects of these networks. To detect the emergence of new areas from the hundreds of users based on the responds in social network posts. A probability model is proposed for mentioning behavior of social networks by the number of mentions per post and the occurrence of users taking place in the mentions. The basic assumption is that a new emerging topic is something people feel like discussing, stating or forwarding the data further to their friends. In the proposed system the link anomaly model is combined with word based and text based approach
@article{Ramya_2015,
abstract = {Detecting the emerging areas becomes interest by the fast development of social networks. As the information exchanged in social networks post include not only the text but also images, URLs and video therefore conventional-term-frequency-based approaches may not be appropriate in this context. Emergence of areas is focused by social aspects of these networks. To detect the emergence of new areas from the hundreds of users based on the responds in social network posts. A probability model is proposed for mentioning behavior of social networks by the number of mentions per post and the occurrence of users taking place in the mentions. The basic assumption is that a new emerging topic is something people feel like discussing, stating or forwarding the data further to their friends. In the proposed system the link anomaly model is combined with word based and text based approach},
added-at = {2015-08-11T08:02:22.000+0200},
author = {K.Ramya and Rajakumari, S. Brintha and Nalini, Dr. T.},
biburl = {https://www.bibsonomy.org/bibtex/2d52d96d20043e93d56b3d86af3ba9225/ijritcc},
doi = {10.17762/ijritcc2321-8169.150396},
interhash = {2b1bd405dc7a19c896791c22936af88d},
intrahash = {d52d96d20043e93d56b3d86af3ba9225},
journal = {International Journal on Recent and Innovation Trends in Computing and Communication},
keywords = {Anomaly Burst Sequentially Social Topic coding detection discounted maximum-likelihood networks normalized},
month = {march},
number = 3,
pages = {1338--1343},
publisher = {Auricle Technologies, Pvt., Ltd.},
timestamp = {2015-08-11T08:02:22.000+0200},
title = {Detecting Emerging Areas in Social Streams},
url = {http://dx.doi.org/10.17762/ijritcc2321-8169.150396},
volume = 3,
year = 2015
}