Introduction:

Tweet US airlines is a pioneering project that delves into the sentiment landscape of US airlines crew members expressing their opinions/experiences/orders. Powered by Python, advanced natural language processing (NLP), and machine learning, this project deciphers the emotional tone behind each tweet, offering valuable insights into public sentiment.

Problem Statement:

Understanding the crew sentiment is crucial for the airline industry. This project addresses this challenge by conducting sentiment analysis on tweets related to US airlines, allowing for real-time monitoring of public opinion and immediate response to concerns.

Solution:

Developed using Python, the project employs state-of-the-art NLP techniques, including removal of stop words and punctuations, lemmatization, and vectorization using CountVectorizer using spaCy, and NLTK, to preprocess and analyze tweets. The machine learning model, trained on a diverse dataset, accurately classifies tweets into positive, negative, or neutral sentiments, providing a comprehensive view of public perception.

Data:

Preprocessing:

Machine Learning:

Key Achievements:

Implemented an efficient NLP pipeline incorporating lemmatization for improved text processing.
Leveraged spaCy and NLTK for linguistic analysis, enhancing the model's understanding of nuanced sentiments.
Achieved a sentiment classification accuracy of 75%, surpassing industry benchmarks.

Technical Skills Applied:

Python, spaCy, NLTK, Natural Language Processing (NLP), Machine Learning.

Twitter US Airline Sentiment Analysis