BIRCH: an efficient data clustering method for very large databases
SIGMOD '96 Proceedings of the 1996 ACM SIGMOD international conference on Management of data
Automatic subspace clustering of high dimensional data for data mining applications
SIGMOD '98 Proceedings of the 1998 ACM SIGMOD international conference on Management of data
A Spectral Algorithm for Seriation and the Consecutive Ones Problem
SIAM Journal on Computing
Construction of conceptual graph representation of texts
HLT-SRWS '04 Proceedings of the Student Research Workshop at HLT-NAACL 2004
Graph clustering using the weighted minimum common supergraph
GbRPR'03 Proceedings of the 4th IAPR international conference on Graph based representations in pattern recognition
Hi-index | 0.00 |
In the field of information processing, most of the existing text clustering algorithm is based on Vector Space Model(VSM). However, VSM can not effectively express the structure of the text so that it can not fully express the semantic information of the text. In order to improve the ability of expression in the semantic information, this paper presents a new text structure graph model. With the weighted graph, this model expresses the characteristics term of the text and its associated location information. On this basis of spectral graph seriation, a spectral clustering algorithm is put forward. This algorithm replace solving common subgraph with matrix computation, then reduce the computational complexity of graph clustering. There are also algorithm analysis and experiment in the paper. The results of the study show that the text clustering algorithm based on spectral graph seriation is effective and feasible.