Sentiment analysis is a text analysis technique that detects polarity (e.g. a positive or negative opinion) within text, whether a whole document, paragraph,sentence, or clause. Sentimentanalysis is also known as opinion mining. Understanding people’s emotions is essential for businesses since customers express their thoughts and feelings more openly than ever before. The commonly used social media platform to express one’s opinions or emotions is Twitter.
Performing analysis on customer feedback, such as opinions in survey responses and social media conversations, allows brands to listen attentively to their customers, and tailor products and services to meet their needs. However, all the opiniated data from the Twitter is in the form of text which is unstructured. . Sentiment analysis, however, helps businesses make sense of all this unstructured text by automatically understanding, processing, and tagging it.
Objective of this project is to perform sentiment analysis on the tweets of six US Airlines. The scrapped tweets contain positive, negative, or neutral sentiments about the airline from their respective customers. The task is to analyze how travelers in February 2015 expressed their feelings on Twitter about six major US airlines. Few of the algorithms used for sentiment analysis are Naive Bayes, SVM, Logistic Regression and LSTM. Out of them, in this project Naïve Bayes classifier is used to build the sentiment analysis model for the US Airline Tweets. The classifier is hard coded in Python without using any libraries with inbuilt classifiers.
Dataset: The dataset is borrowed from Kaggle @ https://www.kaggle.com/crowdflower/twitter-airline-sentiment . The datafile is available in this repo.