Research on Discovery of BBS Topic Based on Clustering
Xiang Wu · Journal of Anhui Normal University · 2009
To obtain BBS topic effectively has been an important research field of web information processing.By analyzing the shortage of existing topic discovery algorithms,a new discovery method is put forward.Based on clustering,the method is to calculate the similarity between comments using latent semantic analysis and cluster the topics with the factors of time and space.Finally,the visual and interactive system is implemented,which can discover topic drift and new topic timely and effectively.