Opinion Mining and Sentiment Analysis for Amazon Product Reviews using Lexicon and Rule-Based Approach and Testing on Machine Learning Algorithms

  IJCTT-book-cover
 
International Journal of Computer Trends and Technology (IJCTT)          
 
© 2018 by IJCTT Journal
Volume-58 Number-1
Year of Publication : 2018
Authors : Sai Kiran Chintalapudi, Harshavardhan Metla, Keerthi Shrikar , Nalluri Rahul
  10.14445/22312803/IJCTT-V58P107

MLA

Sai Kiran Chintalapudi, Harshavardhan Metla, Keerthi Shrikar , Nalluri Rahul, "Opinion Mining and Sentiment Analysis for Amazon Product Reviews using Lexicon and Rule-Based Approach and Testing on Machine Learning Algorithms". International Journal of Computer Trends and Technology (IJCTT) V58(1):40-45, April 2018. ISSN:2231-2803. www.ijcttjournal.org. Published by Seventh Sense Research Group.

Abstract
As people are free to say their opinions on anything using various social networking sites like Twitter, Facebook, Discussion forums, and blogs. Particularly Microblogging and text messaging have emerged and become dominated tool over the web. Amazon Reviews are often used to share opinions and sentiments about the products they purchased the products. The availability of social content generated on sites such as Amazon creates new opportunities to study public opinion about the entity. This analysis we took amazon data for sentiment classification. The Sentiment analysis is done on a per-review basis. The words in each review are compared with those in other reviews that have been previously labeled as “positive”, “negative” or “neutral”. After looking at these words, the algorithm then judges whether the text in the Tweet is positive or negative or neutral based on the likelihood for each possibility. The overall objective of this paper is to determine the sentiment of the text, whether it is positive, negative or neutral, which is extended to strength of polarity also this approach is used to obtain the significant features and to analyzing the overall sentiment for each object by using training data and testing data using Machine Learning Algorithms: Naïve Bayes Algorithm and Support Vector Machines(SVM) Algorithm.

References
[1] Sentiment Analysis : A Literature Review, 8-9 Nov. 2012, Management of Technology (ISMOT), 2012 International Symposium
[2] A Literature review on Sentiment Analysis - Vol- 3 issue- 5, 2017 IJARIIT
[3] What is Sentiment Analysis? Lexalytics
[4] Understanding Sentimental Analysis: What it is and why is it used - Kristian Bannister, Brandwatch.
[5] Introduction to Sentiment Analysis - Algorithmia Blog.
[6] Opinion Mining and Sentiment Analysis - cornell.edu.

Keywords
Web sentiment analysis, Opinion mining, Vader tool, Support Vector Machines, Naïve Bayes Algorithm, Recommendation system