SENTIMENT ANALYSIS AND PREDICATION MODEL
Vaishnavi Vats, Parth Garg, Vishwajeet Singh, Shikhar Yadav · International Journal of Engineering Applied Sciences and Technology · 2020
Sentiment analysis on social media is a crucial a part of today's need for operation.Different machine learning techniques are utilized in recent years, and usage of an emoticon analytical to automatically annotate training sets has been a well-liked advent.As emojis are getting more popular to use in text-based elucidation this presumption explores the viability of an emoji training analytical for multi-class sentiment analysis employing a Multinomial Naive Bayes Classifier.Training sets consisting of 4000 to 400 000 tweets were wont to train the classifier using various configurations of N-grams.The results show that an emoji analytical accomplishes well compared to emoticon-or hashtag-based analytics.However, classifier befuddled is very hooked in to class selection and emoji depictions when multiclass sentiment analysis is accomplished.I.