Title :
Validity Strategy Research Based on Theme Search
Author :
Meng, Qiang ; Geng, Xinyu ; Yang, Li ; Tang, Jie ; Dong, Linlin
Abstract :
The validity of the web content which is craweled based on theme search does not make us very satisfied. This article adopts genetic algorithm to realize subject extraction, block processing of the page content, the validity verification with subject. Finally we grab pages that have high correlation with themes. Experimental results show that the method is feasible and improve the effectiveness of the theme search.
Keywords :
Containers; Correlation; Crawlers; Genetic algorithms; Genetics; Noise; Web pages; Topic crawler; genetic algorithm; noise; page text extraction; theme relevance;
Conference_Titel :
Computational and Information Sciences (ICCIS), 2011 International Conference on
Conference_Location :
Chengdu, China
Print_ISBN :
978-1-4577-1540-2
DOI :
10.1109/ICCIS.2011.310
