A method for sorting out the spam from Chinese product reviews

Author

Lijia Liu ; Yu Wang

Author_Institution

Coll. of Math. & Comput. Sci., Hebei Univ., Baoding, China

fYear

2012

fDate

21-23 April 2012

Firstpage

35

Lastpage

38

Abstract

This paper conducts a research on the spam detection in the field of Chinese product reviews. As to useless reviews, the paper uses four important classification features based on questions, hyperlinks and so on to characterize reviews, and then adopts the classification method based on the Logistic regression to detect the useless reviews. As to those untruthful reviews, firstly 2-gram model is proposed to characterize reviews with the consideration of the word order, then the Katz smoothing method is adopted to smooth the model, and lastly the KL divergence is added to detect the untruthful reviews. The experiments have illustrated that those methods put forward in this paper can effectively detect the spam in the field of Chinese product reviews.

Keywords

advertising data processing; pattern classification; regression analysis; unsolicited e-mail; 2-gram model; Chinese product reviews; KL divergence; Katz smoothing method; classification features; classification method; hyperlinks; logistic regression; questions; review characterization; spam detection; spam sorting out method; untruthful review detection; useless review detection; Decision support systems; Zinc; 2-gram model; KL divergence; Katz smoothing; Logistic regression; Spam detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Electronics, Communications and Networks (CECNet), 2012 2nd International Conference on

Conference_Location

Yichang

Print_ISBN

978-1-4577-1414-6

Type

conf

DOI

10.1109/CECNet.2012.6201665

Filename

6201665