US Airlines on Twitter

Fred Zeng
Posted on Jun 28, 2019

Introduction

As technology grows and globalization develops, more and more consumers are using airplanes as their mode of transportation. With so many choices when it comes to flying, and so many airlines in the U.S. competing with each other, it is valuable to analyze the feedback given by consumers on Twitter. This study therefore takes this data set from Kaggle, with more than 14,000 tweets during the month of February 2015 over 6 major U.S. airlines. This data includes an overall rating, which can be negative, positive or neutral, along with their comments. The RShiny visualization can be viewed at https://fredzeng.shinyapps.io/shinyDashBoard/ and the code at https://github.com/freddy90503/ShinyProject.

Overall

First I created a graph that shows the difference in quantity of reviews by three levels of rating. We can see that most of the tweets were negative. After that, I created two graphs to visualize how each individual airline performs. We can see that United Airlines has the most reviews but also has the highest negative percentage rate, while Virgin America has the fewest reviews but also the lowest negative rate.

By Airlines

Next, I conducted an analysis on each airline over three different charts in order to visualize passengers' reviews from three different perspectives.

By Words

After that, I aggregated keywords from each airline's comments to visualize the key reasons people didn't enjoy their experience. First I conducted a word count for each airline, and then built a heat map, followed by word clouds of the negative reviews. 

By Location

Following that, I visualized the aggregation of IP addresses that came with the data set with a map to identify where users are located. We can see that  the majority of users are from North America, some are from Europe, and a small amount from Southeast Asia. 

Conclusion

With this project, I was able to gain some key insights:

  • Most Internet users did not enjoy their experiences with major US airlines.
  • The best airline of the six is Virgin America, and the worst is United Airlines.
  • The top three reasons for negative reviews are bad customer service, delays, and cancellations.

The last insight is particularly important, as to improve ratings and customer retention, I would advise airlines to focus on identifying why poor service, delays, and cancellations occur. Indeed, with more time, that is where I would take this project: I would expand my data set and perform statistical regressions to help narrow down those root causes.

About Author

Fred Zeng

Fred Zeng

Fred received his M.S. in management and systems with a concentration in database technology from New York University. He was also a business and website analyst intern at NYU, for his research, he designed and conducted data testing...
View all posts by Fred Zeng >

Leave a Comment

No comments found.

View Posts by Categories


Our Recent Popular Posts


View Posts by Tags

2019 airbnb alumni Alumni Interview Alumni Spotlight alumni story Alumnus API artist aws beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Big Data bootcamp Bootcamp Prep Bundles California Cancer Research capstone Career citibike clustering Coding Course Report D3.js data Data Analyst data science Data Science Academy Data Science Bootcamp Data Scientist Data Scientist Jobs data visualization Deep Learning Demo Day dplyr employer networking feature engineering Finance Financial Data Science Flask gbm Get Hired ggplot2 googleVis Hadoop higgs boson Hiring hiring partner events Industry Experts Job JP Morgan Chase Kaggle lasso regression Lead Data Scienctist Lead Data Scientist leaflet linear regression Logistic Regression machine learning Maps matplotlib Medical Research meetup Networking neural network Neural networks New Courses nlp NYC NYC Data Science nyc data science academy NYC Open Data NYCDSA NYCDSA Alumni Open Data painter pandas Portfolio Development prediction Programming PwC python python machine learning python scrapy python web scraping python webscraping Python Workshop R R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest recommendation recommendation system regression Scrapy scrapy visualization seaborn Selenium sentiment analysis Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Tableau Testimonial tf-idf Top Data Science Bootcamp twitter visualization web scraping What to expect word cloud word2vec XGBoost yelp