The data will set you free. What does Twitter sentiment analysis say about major Airlines?
This Twitter data was scraped from February of 2015 and contributors were asked to first classify positive, negative, and neutral tweets, followed by categorizing negative reasons (such as “late flight” or “rude service”). Thanks CrowdFlower for the data.
Raw number of tweets, segmented by Sentiment
- United had the highest raw volume of negative tweets.
- US Airways had the highest percentage of negative tweets.
- Southwest had the highest raw volume of positive tweets.
- Virgin America had the highest percentage of positive tweets.
Breakdown of negative sentiment, by airline, by reason
- Damaged Luggage and Long Lines represented the smallest percentage of the negative sentiment tweets.
- Likewise, Customer Service Issues and Late Flights represented the largest percentage of the negative sentiment tweets.
- Delta had the most Late Flight tweets, on a percentage basis, by~ 7%.
- United had the most Lost Luggage tweets, on a percentage basis, by ~4%.
- US Airways had the most Customer Service Issue tweets, on a percentage basis, by ~4%.
- Virgin America had the least Flight Attendant, Late Flight and Lost Luggage tweets, on a percentage basis.
- Delta had the least Canceled Flight and Flight Booking Problems tweets on a percentage basis.
Geotags of the tweets
- Curiously, there were plenty of international expressions of sentiment, although this data was primarily about american (the country) flights.
Get the raw data
Here is a link to the raw data.
Leave a comment
What do you think? Leave me a comment via twitter via @owocki.