Title :
One methodology for spam review detection based on review coherence metrics
Author_Institution :
Coll. of Inf., Mech. & Electron. Eng., Shanghai Normal Univ., Shanghai, China
Abstract :
In this paper, we propose an iterative computation framework to detect spam reviews based on coherent examination. We first define some reviews´ coherent metrics to analyze review coherence in the granularity of sentence. Then the framework and its evaluation process are discussed in details.
Keywords :
Internet; iterative methods; retail data processing; security of data; software metrics; unsolicited e-mail; consumer online shopping; e-business Web site; iterative computation framework; product review; review coherence metrics; sentence granularity; spam review detection; coherence metric; spam review detection; word concurrence probability; word transition probability;
Conference_Titel :
Intelligent Computing and Internet of Things (ICIT), 2014 International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4799-7533-4
DOI :
10.1109/ICAIOT.2015.7111547
