Abstract

Sentiment analysis or opinion mining is a technique that involves building system that can identify and extract opinions from text. The process of deriving opinions from piece of text to determine writer's views towards a particular topic or product is positive, negative or neutral also termed as opinion mining. In this paper, analysis of numerous tweets related to the no plastic campaign is performed to predict the degree of polarity and subjectivity of tweets. The analysis is divided into phases: extracting data, pre-processing, cleaning, removing stop words, and calculation of sentiment scores. The machine learning approach is applied on dataset related to the no plastic campaign and analysis is done. The extraction of neutral tweets, to distinguish it from the mainstream tweets, has also been approached. Hashtags and emoticons are the relevant Twitter specific features. Emoticons can be positive or negative. Determining and extracting useful information from the emoticons is also a major aspect of this paper. Neutral tweets are also separated well from the mainstream tweets so that the accuracy of positive tweets can be extracted well to get a final overview of how the masses collectively reveal to such government-based campaigns.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call