I really hate flying, not because I do not like being transported through the sky in a giant metal cylinder which is incredibly amazing and cool, but because service is unpredictable. Inevitably, I am burdened with mundane research, searching for and reading recent reviews, to find a good service. No one really wants to do this, but we still want to know which airlines have a greater percentage of recently satisfied customers. PeopleBrowsr, a social search engine we are working with, did a really interesting sentiment analysis task on airlines and generously allowed us to publish the data.
We can see a slight negative correlation between size of the airline and the percentage of positive tweets. Smaller commercial airlines like Hawaiian, SkyWest, and Virgin had higher percentages of positive tweets clustering towards the lower right hand corner of the graph, while larger carriers like United, Delta, and Continental had lower percentages clustering towards the upper left hand corner. Though SouthWest was one of the larger carriers that broke this trend. We should note that Aloha Airlines no longer exists (the passenger data for which is from 2007) and it’s possible that the tweets for Aloha airlines showed such a high percentage of positive tweets because “aloha” invokes positive sentiment.
What was said
To gain insight into what we can expect from a positively or negatively viewed airline, it would also be nice to know what words were being used. So below are two nice Wordle visualizations of tweeted words where size indicates greater prevalence of the word, while word orientation and color are for style.
Positive Sentiment Tweet Words
Negative Sentiment Tweet Words
Not surprisingly the prevalences of the words “delay”, “wait”, and “waiting” for negatively viewed airlines implies having delays and making people wait is bad. Positive tweets contained common words like “great”, “best”, and “good”, but also “internet”, “wifi”, and “wireless” which is also not very surprising, since internet connectivity is so highly valued. Interestingly, some positive tweets contain words like “galactic”, “mothership”, and “spaceport”. Taking this into account I’ll try to find an airline run by aliens the next time I fly, and hopefully my interactions with them won’t prove disastrous.
-John
Kung Fu Kid
This pretty much reminds me of the quote from Alan Shepperd who said “it’s a very sobering feeling to be up in space and realize that one’s safety factor was determined by the lowest bidder on a government contract.”
I’m sure the same goes for much of what we rely on from airlines…. A good reason to hate flying me thinks!
Kung Fu Kid
Jez Liberty
Wow! Cool word visualisation!!
Is this an app or something else??
I am definitely going to check peopleBrowsr! What a cool tool with lots of application this could have (ie I am thinking contrarian investing trends, etc.)
ohohoh very exciting!!
Thanks for the great post Dolo!
Shawn Phillips
Great data set on a damn shame subject.
Too bad the US airlines are intent on taking the air out of flying…
Seems whenever I travel airlines from EU or AU, they are swift, helpful, clean and fun. Really frustrating.
Final thought, myself and Warren Buffet are relieved to not find the Gulfstream G5 from NetJets up here! Ha…
In Strength,
Shawn Phillips
Jonathan Rockway
I disagree with Shawn, outside of the US it is very hard to find good customer service. AA is always happy to help me in any situation, but non-US airlines like BA and JL are generally non-helpful. (I have also found BA flight attendants to generally not be very nice; at least compared to AA flight attendants.)
Worth noting that CX and KA are an exception, they are always helpful and super-nice.
Bob Carpenter
There’s an unmodeled effect here. The airlines with low sentiment are “full service” that provide connections all over the world, including to tiny airports. To do this, they need large networks and can’t be choosy about which airports they fly to. The high sentiment airlines are all more point-to-point oriented. Flying the point-to-point model lets you pick your destinations and times more freely, and leads to fewer network-induced delays. There may also be a strong business vs. vacation issue here, too. And maybe people are just happier going to Hawaii?
John
Thanks for your comments.
@Bob – I completely agree; there is definitely an unmodeled effect. The number of passengers is most likely not that causal effect for lower sentiment. Rather, as you mentioned, certain variables like whether an airline can fly directly to particular locations are probably greater determinants of sentiment. While researching I stumbled upon JetBlue’s press reports where they mention some of their competitive advantages, like being able to use and maintain younger aircraft, which a larger airline like United or Delta would probably find more difficulty implementing (for 2008 from pdf pages 10 to 30 or so, and found at http://investor.jetblue.com/phoenix.zhtml?c=131045&p=irol-reportsAnnual). I almost sound like an advertiser for JetBlue but I’ll grant that their information was easiest to find and the information provided was very detailed such that more insights could probably be derived.
Gaurav
It turns out that the government tracks and shares a fairly rich dataset regarding airline arrival times (http://www.transtats.bts.gov/OT_Delay/OT_DelayCause1.asp), I wonder how sentiment tracks against actual performance?
It would be pretty interesting to see if any divergence between perception and reality of airline performance is correlated with other effects. Piggybacking on Bob’s suggestion above, perhaps “work vs vacation”?