The goals of this project are 1) build a model for six major U.S. airlines that
performs sentiment analysis on customer reviews so that the airlines can have fast
and concise feedback, 2) make recommendations on the most important aspect
of services they could improve given customers’ complains. In this project, we
performed multi-class classification using Naive Bayes, SVM and Neural Network
on the Twitter US Airline data set from Kaggle. Significant accuracy has achieved,
which shows that our models are reliable for future prediction.