Sentiment Analysis for Popular e-traveling Sites in Indonesia using Naive Bayes

Users of online ordering and/or purchase services on the marketplace often face difficulties in determining which objects or services are selected closest to the criteria of potential users. The rating or rating feature used by many marketplaces is sometimes not objective and does not match the content of reviews given by the reviewers. This results in a decrease in the level of user confidence in the ratings and ratings provided by the service. Therefore, the prospect will seek to obtain a thorough analysis, by reading and analyzing any reviews related to a particular product or service. The burden for users is the number of reviews that are not small and the use of different language styles. This Research proposes a method that can provide a rating value that is more in line with the content of the review with respect to the sentiments present in the review. The method developed utilizes a corpus built on the topic model of reviews on the site of the hotel service provider as well as articles relating to the hotel. The sentiment analysis was obtained by using the Naïve Bayesian classification method and the use of probabilistic value of the corpus. The results of the test show the success rate of methods in analyzing sentiment is 89%. The result of sentiment analysis is used as reference of calculation of rating value.

[1]  Ivan Titov,et al.  Modeling online reviews with multi-grain topic models , 2008, WWW.

[2]  Yong Shi,et al.  The Role of Text Pre-processing in Sentiment Analysis , 2013, ITQM.

[3]  Meng Wang,et al.  Topic and Sentiment Unification Maximum Entropy Model for Online Review Analysis , 2015, WWW.

[4]  Harry Zhang,et al.  The Optimality of Naive Bayes , 2004, FLAIRS.

[5]  Claire Cardie,et al.  Multi-aspect Sentiment Analysis with Topic Models , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[6]  Mohamad Irfan,et al.  The comparation of text mining with Naive Bayes classifier, nearest neighbor, and decision tree to detect Indonesian swear words on Twitter , 2017, 2017 5th International Conference on Cyber and IT Service Management (CITSM).

[7]  Ben Shneiderman,et al.  Readings in information visualization - using vision to think , 1999 .

[8]  Vaibhavi N Patodkar,et al.  Twitter as a Corpus for Sentiment Analysis and Opinion Mining , 2016 .

[9]  Marie-Francine Moens,et al.  Automatic Sentiment Analysis in On-line Text , 2007, ELPUB.

[10]  Alice H. Oh,et al.  Aspect and sentiment unification model for online review analysis , 2011, WSDM '11.

[11]  Syopiansyah Jaya Putra,et al.  Context for the intelligent search of information , 2017, 2017 5th International Conference on Cyber and IT Service Management (CITSM).

[12]  M. O. Hoda,et al.  Online Paper Review Analysis , 2015 .

[13]  Valentin Jijkoun,et al.  Generating Focused Topic-Specific Sentiment Lexicons , 2010, ACL.

[14]  Hinrich Schütze,et al.  Introduction to information retrieval , 2008 .

[15]  Alan F. Smeaton,et al.  Topic-dependent sentiment analysis of financial blogs , 2009, TSA@CIKM.

[16]  Jürgen Broß,et al.  Aspect-Oriented Sentiment Analysis of Customer Reviews Using Distant Supervision Techniques , 2013 .

[17]  Tata Sutabri,et al.  Framework of sentiment annotation for document specification in Indonesian language base on topic modeling and machine learning , 2017, 2017 5th International Conference on Cyber and IT Service Management (CITSM).