Open AccessTwitter Sentiment Analysis and Visualization Using Apache Spark and Elasticsearch
Author(s) -
G. Maragatham,
Shobana Devi A
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.12.16049
Subject(s) - sentiment analysis , computer science , popularity , world wide web , the internet , big data , social media , population , key (lock) , spark (programming language) , information retrieval , data science , artificial intelligence , data mining , psychology , social psychology , demography , computer security , sociology , programming language
Sentiment analysis on Twitter data has paying more attention recently. The system’s key feature, is the immediate communication with other users in an easy, fast way and user-friendly too. Sentiment analysis is the process of identifying and classifying opinions or sentiments expressed in source text. There is a huge volume of data present in the web for internet users and a lot of data is generated per second due to the growth and advancement of web technology. Nowadays, Internet has become best platform to share everyone's opinion, to exchange ideas and to learn online. People are using social network sites like facebook, twitter and it has gained more popularity among them to share their views and pass messages about some topics around the world. As tweets, notices and blog entries, the online networking is producing a tremendous measure of conclusion rich information. This client produced assumption examination information is extremely helpful in knowing the supposition of the general population swarm. At the point when contrasted with general supposition investigation the twitter assumption examination is much troublesome because of its slang words and incorrect spellings. Twitter permits 140 as the most extreme cutoff of characters per message. The two procedures that are mostly utilized for content examination is information base approach and machine learning approach. In this paper, we investigated the twitter created posts utilizing Machine Learning approach. Performing assumption examination in a particular area, is to distinguish the impact of space data in notion grouping. we ordered the tweets as constructive, pessimistic and separate diverse people groups' data about that specific space. In this paper, we developed a novel method for sentiment learning using the Spark coreNLP framework. Our method exploits the hashtags and emoticons inside a tweet, as sentiment labels, and proceeds to a classification procedure of diverse sentiment types in a parallel and distributed manner.