ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Big Data Approach of Sentiment Analysis of Twitter Data using K-Mean Clustering Approach

Journal: International Journal of Mechanical and Production Engineering Research and Development (IJMPERD ) (Vol.10, No. 3)

Publication Date:

Authors : ; ;

Page : 6127-6134

Keywords : : K-means; Clustering; Sentiment analysis; Bigdata; Bigdata sentiment & Twitter data;

Source : Downloadexternal Find it from : Google Scholarexternal


The social networking sites are storming with vast amount of information is produced and processed. This production of enormous amount of data from different microblogging platforms needs to be stored and processed by Big data approach. The data generated in peta bytes from social media platforms is called big data. Most of the world populations are sharing their opinion and feedback every day on micro blogging sites, the opinion and behavior of the user on microblogging site is tedious. Number of devices, laptops, iPad, Tabs, MacBook and distinct IOT data gadgets produced enormous amount of data. The processing and retrieving of this huge amount of data becomes a very complicated task. Nowadays social media is playing a crucial rule in our day to day life. The social media platforms have been greatly used for expressing human opinions for the item and verities of services. The business of different organizations is based on the feedbacks and rating of millions of the microblogging site uses can be used to extract their opinion, attitudes and sentiment towards the products. This feedback information on social media used for the future market of the business improvement and analysis of the product performance. The extracting the user's opinion from the social media platforms is a difficult task; it can be redefined into various ways. In this paper, an open source approach is presented, and data is collected from tweets from twitter API, analyzed and visualized these tweets using python. To analyze sentiments of tweets we have used K-Means clustering algorithm and implemented with Python programming language. This sentiment analysis is based on the tweets data retrieval from different sources and then classifying the user perspectives in different classifications accuracy and two unique sentiments (positive and negative).The process of sentiment analysis is the computational procedure that deciding the output by the proposed method is positive or negative. In this paper, an endeavor has been modelled to prefer analysis method for sentiment of twitter dataset. In the proposed technique polarity of each tweet is calculated to differentiate whether the tweet is neutral, positive or negative. The sentiment sentence's polarity is the emotions of user such as angry, sad, happy and joy. The proposed entire research work processed and implemented using Python

Last modified: 2020-12-08 14:34:12