Title :
Utilizing improved Bayesian algorithm to identify blog comment spam
Author :
Aiwu, Li ; Hongying, Liu
Author_Institution :
Dept. of Comput. Sci., Guangdong Vocational Coll. of Posts & Telecom, Guangzhou, China
Abstract :
In this paper, according to the blog website team dealing with comment spam demand more and more, analyzed the traditional Bayesian algorithm based on statistical method of defects, pointed out the deficiency in practical application, improved the rough Bayesian algorithm, utilized a string of comments appear based on the garbage probability value, calculated the number of geometrical average algorithm. The experimental results show that the modified Bayesian classification algorithm can effectively improve the classification of spam effect, garbage afr, legal review comments afr and average afr has dropped substantially.
Keywords :
Bayes methods; Web sites; pattern classification; security of data; statistical analysis; Bayesian classification algorithm; average AFR classification; blog Website team; blog comment spam identification; comment spam; defects statistical method; garbage AFR classification; garbage probability value; geometrical average algorithm; legal review comments AFR classification; spam effect classification; Algorithm design and analysis; Bayesian methods; Blogs; Classification algorithms; Libraries; Unsolicited electronic mail; Bayesian algorithm; blog comment spam; geometric mean algorithm;
Conference_Titel :
Robotics and Applications (ISRA), 2012 IEEE Symposium on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4673-2205-8
DOI :
10.1109/ISRA.2012.6219215
