This is our blog. We write about cool experiments, interesting case studies, open talks and technicalities.
Grab the RSS feed
Back

2017-04-24

What makes airline passengers happy?

A few of the high-profile carriers, that are currently scoring well, may be dangerously relaxed about their service and may soon fall out of grace, and a few contenders are posed to take their place.

It is possible that observed trends in perceived service may be the best predictors for relative changes in passenger satisfaction, overall rating, loyalty and so on and forth.

These are some the generalizations emerging from analyzing just the qualitative data, in the form of 20000 passenger reviews, in free-text, covering 22 carriers: Air China, Air France, All Nippon Airways, American Airlines, British Airways, Cathay Pacific Airways, China Eastern Airlines, China Southern Airlines, Delta Airlines, Emirates, Etihad, Lufthansa, Norwegian, Qantas, Qatar, SAS, Singapore Airlines, Southwest Airlines, Thai Airways, Turkish Airlines, United Airlines, Virgin Atlantic.

Service is the most important variable for the overall passenger experience and satisfaction.

Service drives the perception of most other aspects, including seat comfort and even food and drink. Generally speaking: passengers that feel ignored will not appreciate the service, and they will not appreciate their seat, their food, or most other things, nearly as much as they otherwise would.

Airline passengers seem to put up with almost anything, as long as they feel that they are being seen and looked after – as individuals.

The satisfaction score (2nd columns) is derived from free-text only, but the satisfaction score corresponds reasonably well with known polls carried out in order to rate airlines for various top lists and awards.

The 3rd column lists the most obvious areas for improvement for each of the 22 carriers in the analysis. This is, the percentage of passengers, that complain about different things.

It’s not really about the food or the seat

The happiest passengers (i.e. the passengers of the top-5 carriers in terms of or satisfaction score) complain to a small extent, and when they complain it’s about their food (average 9,4%), their seats (average 7,3%), and their service (average 4,1%) and sometimes about the entertainment or the wifi, or similar. Within brackets is the average prevalence, within the top-5 carriers, of negative value judgements for each theme subject to complaint: Food, Seat & Service.

The least happy passengers (i.e the passengers of the bottom-5 carriers in terms of our satisfaction score) complain a great deal and, and they complain loudly about their service (average 21,9%) , their food (average 15,3%), and their seats (average 9,6%). 

The overall satisfaction score is based on the absolute difference in volume between the positive and negative percentages of observed general value judgements for each airline, hence normalizing the values, whilst taking into account both differences in data volumes and the differences deriving from the fact that some airlines evoke more emotions and value judgements than others.

The bottom-5 in this study, with the least happy passengers, all have huge potential in terms of improving their service, which is the dominating factor for overall perception and experience. 

Looking at these figures, one may think that the top-5 airlines with the happiest passengers need to improve their food & beverages, their seats and their inflight entertainment. That would, however, be the wrong conclusion and the wrong focus:

These top-5 airlines should just continue to focus their efforts on the one thing that really counts more than anything else: Service.

It seems that when people are generally happy they always find some small thing that could be improved, and food is not the most important thing in this context. The perceived service affects the satisfaction with everything else, including the sensation of most aspects of the experience.

Even the perceived seat comfort and the taste of the food depend largely on the quality of the service: Improve the service and the food will taste better, the seat will become more comfortable, the inflight entertainment improves. It’s automatic, and if you are professionally active in this field, you are aware of this.

Interestingly, having to pay for one’s meal may affect the food experience positively. We will track that possible phenomenon over time, and investigate further.

What aspects of service matter most?

What aspects of service actually matter? A picture emerges that would be familiar to any retail banker, private banker, hotelier and restaurateur: Good service is about attention to each customer.

From retail banking we know that the client’s experience of the client meeting is a key variable for profitability. A good meeting is more important than the best offer. An ill-prepared meeting is expensive and it boils down to showing respect for the individual.

From the hospitality sector we know that an individualized invitation for all hotel guests, to the daily free wine-tasting hour, is a key variable for the overall rating and for the profitability, since it makes people feel noticed, and even special.

Unsurprisingly, bad service on airlines is associated with indifferent, irresponsive and un-attentive staff and cabin crew. Good service seems to be about making sure that no passenger feels invisible, ignored or disrespected.

Establishing a minimum level of contact, or rapport with each individual passenger, in order to make each passenger feel seen, is one obvious way to improve the overall passenger experience.

Inflight Internet/Wifi is an emerging theme (on average 10,1%) and highly appreciated, but technical performance issues are problematic from a satisfaction point of view.  

The study

The automated analysis was carried out with Gavagai Explorer.

The study is based purely on qualitative data (no quantitative data): 20000 passenger free-text reviews of 22 airlines. Themes are automatically identified and clustered based on meaning, using the latest language AI for text analytics.

We measure how strongly opinionated reviewers are with regard to different aspects of their experience and we make these values comparable between different carries.

Some themes emerge from the text, with various degrees of prevalence (%) for different airlines: Food, Drink, Seat, Service, Value, Inflight Entertainment, and so on and forth. The themes are measured and weighted (%) against eight standard sentiments (hate, desire, love, skepticism, violence, fear, positive, negative) and each theme has different associated subthemes themes expressed in order of prevalence (%).

Gavagai Explorer

Gavagai Explorer is the market’s leading solution for qual-to-quant conversion, coding and analysis of text data, such as free-text answers from polls and surveys, customer reviews, online mentions, customer support tickets, and other customer interactions.

Gavagai Explorer helps consumer companies and global leaders in insight, analytics, markets research to gain valuable insights from text data without any prior computer skills.

The Gavagai Explorer is operational in 45 languages, including: Albanian, Arabic, Chinese, Czech, Danish, Dutch, English, Estonian, Farsi, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Korean, Latvian, Lithuanian, Malay, Norwegian, Polish, Portuguese, Romanian, Russian, Slovakian, Slovenian, Spanish, Swedish, Swahili, Tagalog/Filipino, Turkish, Thai, Urdu, Vietnamese.

Thank you Kyle Tenn for sharing the analysis!

airline

Category: case studies, Gavagai Explorer, sentiment analysis