by W H Inmon, Forest Rim Technology

It’s no secret. The airlines business is competitive.

There are fare wars. There are frequent flyer clubs. There are airline lounges at major airports. There are new routes being opened up. There are special seat pricing algorithms.

In a word there is constant competition among airlines for the customers and the customers dollars.

At the end of the day the deciding factor on airline traffic is the customer and who the customer chooses for his or her journey. Without the customer there would be no airline. And through the power of making choices the airline customer ultimately determines the economic success of the airline.

So how does an airline start to build customer loyalty? Sure, there are frequent flyer programs. But frequent flyer programs only tell part of the story, because every airline has frequent flyer programs. If an airline is really interested in building customer loyalty, the airline can do something – paradoxically – really simple and really difficult at the same time – listen to what their customers are saying.

Listening to the Customers is Simple in Concept

The customer speaks and the airline listens. But – at the same time – listening to the customer is difficult because –

There are so many customers

There are so many ways the customers can speak

Computers are designed for handling transactions, not language

It simply is not imaginable to think that any person or persons will listen – one at a time – to what the passenger has to say about their experience with the airline. To try to listen to the customer manually is not a possibility. There simply are too many customers all talking at once.

Realistically the only way the airline can listen to the passenger is in an automated manner – using the computer. One of the best ways for the airline to hear what the customer is saying is to turn to the Internet. The Internet is freely available all over the world. The Internet is available 24 hours a day. And the Internet is available to any who can read and write.

For these reasons the Internet is a very good vehicle to capture the voice of the passenger. Indeed when you look at the Internet there are whole collections of feedback from the passenger. Most (but not all) of the comments made by the passenger are in the form of complaints. But even complaints have value when you look at the underlying causes of the complaints.

In Spring of 2016 Forest Rim Technology gathered up a large collection of passenger feedback forms from a wide variety of web sites off the Internet. He information that was gathered was open to the public. Forest Rim gathered the feedback into a textual data set.

The passenger feedback was for the spring of 2016 and the entirety of the year for 2015. The feedback was gathered for both domestic US and for worldwide flights.

The feedback was gathered for all airlines. If an airline only appeared a few times that was because there were only a few mentions of the airline. If the airline appeared many times that was because the number of complaints against the airline were numerous. There was no effort to either include or exclude the complaints for any airline.

The topics covered by the passengers complaints included anything the passenger had on his/her mind.

A typical comment found on the Internet looks like –

Note that the format of the complaint is all text.

All of the complaints were gathered up and processed through Textual ETL.

The text is passed through Textual ETL. Other input to Textual ETL includes taxonomies appropriate to airlines passengers. A standard data base is created. A visualization is then created for the airline passengers complaints.

Of special interest is the fact that not only is the sentiment of the passenger captured, but the reason for the sentiment is captured as well.

The study (visualization by Boulder Insight) looks like –

The first thing of interest is the airlines that were mentioned in the study. The first column shows the airlines that were mentioned and the order of frequency in which they were mentioned.

The second column shows the subjects that were mentioned by the passengers in their complaint ranked by the number of times they were mentioned.

The third column shows the sub rankings for any given column.

As with all dashboards there are many ways to look at the data. One such way is to focus on one airline, then to focus on one aspect of the airline.

In this case the airline chosen is Delta Airlines and the subject that is focused on is luggage. The second column shows the comments made about luggage handling at Delta Airlines.

By using focus and drill down the analyst can get a much clearer picture of what was being said and why.

Furthermore, drill down can continue all the way down to the actual comment that was used to create the analysis in the first place.

While textual ETL can certainly be used for looking at and analyzing publicly available data, Textual ETL can be used to analyze ANY textual data.

To access the airlines study contact Forest Rim. There is no cost for accessing and analyzing the airlines study.


Bill Inmon is the founder of Forest Rim Technology located in Castle Rock, Colorado. Forest Rim Technology produces textual ETL and the data base that can be restructured from Textual ETL. With Textual ETL you can turn document oriented data into an analytical data base that can be analyzed by the computer analyst.