Performance Analysis of Supervised Techniques for Review Spam Detection

Performance Analysis of Supervised Techniques for Review Spam Detection Mr. Ashok Badresiya C.E. Department, Marwadi Education Foundation’s Group of Institutions Rajkot,Gujarat, India ashok.badresiya2011@gmail.com Prof. Saifee Vohra C.E. Department, Marwadi Education Foundation’s Group of Institutions Rajkot,Gujarat, India saifee.vohra@marwadieducation.edu.in Prof. Jay Teraiya C.E. Department, Marwadi Education Foundation’s Group of Institutions Rajkot,Gujarat, India Jay.teraiya@marwadieducation.edu.in ----------------------------------------------------------------------ABSTRACT----------------------------------------------------------Nowadays, millions of products and services are available online. Searching for the best products which targets the individuals’ requirements would be difficult as the result of the existence of too many offers. One of the most useful approaches to choose a product or service is to use the reviews of the others who have already tried them. A reviewing system is a place where individuals write their reviews on their experienced products and services, and also benefit from others’ reviews. Moreover, companies utilize reviewing systems to apply opinion mining techniques in order to improve their goods or services and to watch their competitors. However, the popularity of the reviewing systems ignites this motivation for some people to enter fake review to promote some products or defame competitors products. These review spam should get detected and eliminated in order to prevent misleading potential customers. Opinion mining techniques should use to locate and eliminate potential spam reviews. The objective of this paper is to discover the concept of Review spam detection in the field of opinion mining, and presents a performance analysis of its techniques in this field.

[1]  Yu Wang,et al.  A method for sorting out the spam from Chinese product reviews , 2012, 2012 2nd International Conference on Consumer Electronics, Communications and Networks (CECNet).

[2]  Bing Liu,et al.  Sentiment Analysis and Subjectivity , 2010, Handbook of Natural Language Processing.

[3]  C. K. Bhensdadia,et al.  Improved Decision Tree Induction Algorithm with Feature Selection , Cross Validation , Model Complexity and Reduced Error Pruning , 2012 .

[4]  Jian Pei,et al.  Data Mining: Concepts and Techniques, 3rd edition , 2006 .

[5]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[6]  Yang Wang,et al.  Cost-sensitive boosting for classification of imbalanced data , 2007, Pattern Recognit..

[7]  Masahiko Haruno,et al.  Feature Selection in SVM Text Categorization , 1999, AAAI/IAAI.

[8]  Fatemeh Keshavarz-Rahaghi.  Towards Review Spam Detection , 2013 .

[9]  Claire Cardie,et al.  Finding Deceptive Opinion Spam by Any Stretch of the Imagination , 2011, ACL.

[10]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[11]  Heikki Mannila,et al.  Principles of Data Mining , 2001, Undergraduate Topics in Computer Science.

[12]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[13]  Susan T. Dumais,et al.  Inductive learning algorithms and representations for text categorization , 1998, CIKM '98.

[14]  Oren Etzioni,et al.  Extracting Product Features and Opinions from Reviews , 2005, HLT.

[15]  Alaa El-Halees,et al.  An approach for detecting spam in arabic opinion reviews , 2015, Int. Arab J. Inf. Technol..

[16]  Petra Perner,et al.  Data Mining - Concepts and Techniques , 2002, Künstliche Intell..