29May 2016

SENTIMENT ANALYSIS OF SOCIAL MEDIA DATA USING NAIVE BAYESIAN CLASSIFIER IN HADOOP AND HIVE.

  • Department of Information Technology, Vignan’s Institute of Information Technology, Visakhapatnam, India.
Crossref Cited-by Linking logo
  • Abstract
  • Keywords
  • Cite This Article as
  • Corresponding Author

Sentiment Analysis aims to determine the attitude of a speaker or a writer with respect to some topic or the overall contextual polarity of a document. Tweets are frequently used to express a tweeter's emotion on a particular subject. There are firms which poll twitter for analyzing sentiment on a particular topic. The challenge is to gather all such relevant data, detect and summarize the overall sentiment on a topic. The social media data includes the collection of unstructured raw data from various social media posts & blogs such a Twitter and needs to refine the data to get the results which are most important for understanding the sentiment of a product or service is either positive, negative or neutral. The steps for extracting sentiment data from Twitter and analyzing the performance of a recent iron man3 movie release. we can mine twitter, Facebook and other social media conversations for sentiment data about a company products or movies etc is used to make targeted, real-time, decisions that increase market share. In our project we proposed an architecture, where the raw data taken from twitter is classified and added to HDFS using Naïve Bayesian classifier. Further we process HIVE queries on the sentimental data to catalogue positive, negative and neutral tweets. Subsequently the analysis is illustrated using BI tools. The main advantage of our project is we can visualize divergent tweets on the given attributes and data set according to one’s choice in a map view.


[G.Mani, G.Jyothi, G.Swathi and Ravuri Daniel. (2016); SENTIMENT ANALYSIS OF SOCIAL MEDIA DATA USING NAIVE BAYESIAN CLASSIFIER IN HADOOP AND HIVE. Int. J. of Adv. Res. 4 (May). 176-184] (ISSN 2320-5407). www.journalijar.com


Mani G


DOI:


Article DOI: 10.21474/IJAR01/497      
DOI URL: http://dx.doi.org/10.21474/IJAR01/497