Entity

Time filter

Source Type


Yang H.,Jilin University | Yang H.,Key Laboratory for Symbol Computation and Knowledge Engineering | Wang Z.,Jilin University | Wang Z.,Key Laboratory for Symbol Computation and Knowledge Engineering | And 3 more authors.
Journal of Computational Information Systems | Year: 2010

Most of the existing methods for community discovery only deal with social network with a fixed structure, so they can not effectively deal with dynamic social network. This paper proposes a Multi-agent system method which is applied to real-time dynamic web texts for community discovery. This method combines the multi-agent system control mechanisms with community discovery algorithm. The approach not only divides community for the published web text, but also changes the community division according to the newly updated contents of web texts. Meanwhile, the similarity of two web texts is evaluated through similarity algorithm which compares content similarity and semantic similarity. The effectiveness of this algorithm has been tested on real web texts networks and experiment 3 illustrated the scalability of our algorithm for dynamic community discovery of web texts. © 2010 Binary Information Press. Source


Yang H.,Jilin University | Yang H.,Key Laboratory for Symbol Computation and Knowledge Engineering | Wang Z.,Jilin University | Wang Z.,Key Laboratory for Symbol Computation and Knowledge Engineering | And 3 more authors.
Journal of Computational Information Systems | Year: 2011

The core idea of clustering algorithm is the division of data into groups of similar objects. Some clustering algorithms are proven good performance on document clustering, such as k-means and UPGMA etc. However, few document clustering algorithms pay attention to the hidden sentiment which is a very important feature of the documents. This paper presents an improved k-means algorithm (HSK-Means) based on hidden sentiment vector for Chinese document clustering. Chinese dependency grammar rules are used to extract document feature and evaluate hidden sentiment. A new method for selecting initial cluster centroids based on rank mechanism of similarity is also proposed to improve accuracy of clustering algorithm. The experimental results on real online document sets illustrate that the performance of HSK-Means algorithm is better than classic document clustering algorithms. Copyright © 2011 Binary Information Press. Source

Discover hidden collaborations