High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Sentiment Analysis of product reviews using Hadoop

Author(s):

Rajat Bhat , D Y Patil Institute of Engineering & Technology, Ambi.; Swapnil Gaonkar, D Y Patil Institute of Engineering & Technology, Ambi.; Rohit Biradar, D Y Patil Institute of Engineering & Technology, Ambi.; Snehal Chaudhari, D Y Patil Institute of Engineering & Technology, Ambi.

Keywords:

Hadoop Distributed File System; Map Reduce; Product reviews; Recommender system; Sentiment analysis

Abstract

Sentiment analysis or opinion mining is one amongst the most important tasks of information processing (Natural Language Processing). Sentiment analysis has gain abundant attention in recent years. There is a tendency to aim to tackle the matter of sentiment polarity categorization, that is one amongst the elemental issues of sentiment analysis. Therefore, a way that assigns scores indicating positive and negative opinion concerning the merchandise is planned. It uses Hadoop Distributed File system (HDFS) to store knowledge set and run on MapReduce design for performing sentiment analysis. A general method for sentiment polarity categorization is planned with elaborated method, descriptions knowledge utilized in this study square measure on-line product reviews collected from Amazon.com. Experiments for each sentence-level categorization and review-level categorization square measure performed with promising outcomes. Recommendation system provides the ability to grasp a person’s style and notice new, fascinating content. This would help the organization to decide where they lack, where they need to improve, based on the sentiment analysis carried out using Hadoop.

Other Details

Paper ID: IJSRDV4I120609
Published in: Volume : 4, Issue : 12
Publication Date: 01/03/2017
Page(s): 766-769

Article Preview

Download Article