Abstract effect of text type sentiment analysis classification

Emotion Analysis is the task of determining and classifying the polarity of text content such as social media posts. Sensitivity analysis for Social Media has become a popular topic in academic circles where studies are conducted using open data sets. Social media is an internet-based environment that gives people the opportunity to interact with each other; build virtual networks and communities; information, video, photos, news, ideas etc. Sharing, Twitter, Facebook, Instagram and Linkedin are examples of the most widely used social media platforms. The use of such social media platforms and the data generated for these platforms have increased considerably in recent years, and have begun to attract more attention in many areas such as business, policy and scientific research to gain insight into people's views. This thesis focuses on social media sensitivity analysis using supervised machine learning algorithms such as Naive Bayes, Support Vector Machine, Decision Tree and Logistic Regression classifiers. N-gram modeling was also used. These algorithms and techniques have been applied to three well-known data sets with different characteristics, such as "Stanford Twitter Sentiment", "Sentiment Analysis On Yelp" and "Sentiment Analysis on Movie Reviews" to obtain evaluation results and examine their performance.