@article{MAKHILLJEAS2019141217976,
    title = {Social Media Mining: Analysis of Twitter Data to Find user Opinions about GST},
    journal = {Journal of Engineering and Applied Sciences},
    volume = {14},
    number = {12},
    pages = {4167-4175},
    year = {2019},
    issn = {1816-949x},
    doi = {jeasci.2019.4167.4175},
    url = {https://makhillpublications.co/view-article.php?issn=1816-949x&doi=jeasci.2019.4167.4175},
    author = {K. and},
    keywords = {Sentiment analysis,opinion mining,social networks analysis,Tweets,NLP,GST and R},
    abstract = {Twitter is a social networking and micro blogging service, enabling registered users to read and post
short messages, called “Tweets&#148. Length of Tweets are limited to 140 characters. Twitter allows users to post
photos or short videos. Twitter is one of the most popular social networking site, used by people across the
world for rapid communication and information exchange. Everyday, about 330 million active users use Twitter
to share information and express their opinion. Every second on average, around study 6,000 study Tweets are
published on Twitter which corresponds to over study 350,000 study Tweets sent per minute, study 500 million
study Tweets per day and around study 200 billion study Tweets per year. The volume and variety of data
generated by social media helps businesses in their decision-making. It also helps celebrities in the film
industry, sports and politics to find user opinion about them. Currently, opinion mining and sentiment analysis
is an emerging area for researchers due to ready availability of opinionated data on social networking sites,
review sites and blogs. This data helps in finding different types of sentiments and opinions towards a
particular event or things. Summarizing these opinions can provide valuable insights for businesses. Analysis
of opinions and its classification based on polarity is a challenging task. This study, explains various sentiment
analysis techniques on Twitter data by taking user Tweets about Goods and Services Tax (GST). This study
illustrates the dictionary based approach along with NLP which was used to find the polarity of the Tweets and
classify them.}
    }