Customer Satisfaction of American Airline Companies

Flying on US domestic airlines is a nightmare. The customer service is pathetic, the staff unfreindly, the airlines charge for every small thing…the list goes on and on.

University of Michigan carries out surveys of American customers and publishes the average scores annually as American Customer Satisfaction Index (ACSI). You can check the scores for several industries by visiting their website. For airlines, the chart looks like this:

Screen Shot 2016-04-03 at 5.20.51 PM

American Customer Satisfaction Index for American Airline Companies

The airlines appear in descending order of the 2015 ACSI scores, which range from 81 for JetBlue to 54 for Spirit.

ACSI is published for a given brand only once a year. But companies are interested in knowing about customer satisfaction round the clock. So I decided to use Twitter sentiment as a measure for customer satisfaction. This is a very rough exerise to see whether we get any results that have face validity. My students will realize that, for airlines, Twitter is one of the key social networks for addressing customer complaints. Therefore, Twitter will likely capture customer satisfaction in real time. So the validity is actually about ACSI and not about Twitter sentiment. However, there is a commonly discussed issue about Twitter — it’s not representative of the general population. Still, we must keep in mind that ACSI may not be a good representative of American flyers sentiment either.

I decided to focus on the 9 airlines for which the ACSI scores for 2015 are available – JetBlue, Southwest, Alaska, Delta, American Air, Allegiant, United, Frontier, and Spirit. The graph looks as follows:

ACSI

ACSI Scores for Nine American Airlines

The average score for these 9 airlines is 68.11. As the maximum possible ACSI score is 100,  68 is not a great score. However, I am amazed at how thoroughly the epxectations of American flyers have gone down. I am sure that if the survey respondents were from Asia, you would get an average of less than 50. But that’s a story for another post where I will compare the sentiment about the best airlines including Singapore Airlines, Emirates, Qatar, etc.

Next, I went on Twitter and downloaded tweets that were directed at these airlines. My condition was simply that the Twitter handle of the airline should appear in the tweet. For example, a tweet mentioning @JetBlue would indicate that this is a tweet targeted towards JetBlue and therefore should be included for the analysis. I carried out this data collection on 2 April 2016 from Singapore. Following this, I categorized the tweets as either positive, negative, or neutral. To compare to ACSI, I created a metric similar to Net Promoter Score (NPS). The formula for that is given as follows:

\displaystyle \mbox{Net Sentiment Score} = \frac{\mbox{(Total Positive Tweets - Total Negative Tweets)}}{\mbox{Total Tweets}}

 

Here is the graph when I plotted net sentiment scores of all the 9 airlines:

Twitter sentiment

Net Sentiment Scores for 9 American Airlines

The score is bounded between -1 and 1. If all the tweets are negative then the score will be -1 and if all the tweets are positive then the score will be 1.

The average score is 0.19, which is around 60% of the scale range (1.19/2.0). We see that similar to ACSI graph, 4 airlines–JetBlue, Alaska, Southwest, and Delta–are above the mean while remaining 5 are below the mean. Interestingly, these are the same 4 airlines which have above average scores on ACSI. The ordering is a bit off though. In order to better compare the two graphs, I decided to plot them in the same space. However, for that I need to have the same scale. For the sake of convenience I decided to use Z-scores.¹

Z-scores.png

ACSI and Twitter Net Sentiment Score Correlation

I find that the correlation is high at 0.77. It’s also statistically significant with a p-value equal to 0.016. However, notice that we have only 9 observations, which means that the standard error is likely to be high. Actually the 95% confidence interval for the correlation coefficient is pretty wide [0.21, 0.95] but the lower level is still comfortably far from 0.

I think that ACSI is doing a fair job of capturing customer satisfaction of American air travellers. It corresponds to the Twitter sentiment quite well. It’s worth noting that I am comparing the survey results, which were collected over 1-2 months period in 2015 with tweets that were sent on or slightly before 2 April 2016. It would be worth studying how Twitter sentiment fluctuates over a period of time. This is my next assignment once I am done with the sentiment analysis of top ranked airlines.

In case you are interested in individual airlines sentiment charts, you can view them here:

¹ Z-score of any variable has 0 average and 1 standard deviation.

Instagram Filters and Laziness

I always believed that Instagram filters are what made Instagram such a big hit. Otherwise Instagram was just another photo sharing app. When I started using Instagram, I used to try many filters before settling on one and sharing my picture. Over the period of time, I started sharing pictures without any filters — also known as a “Normal” filter because of my laziness. Recently I wondered whether my behavior was peculiar or many other people were also using Normal filter while sharing pictures on Instagram. Accordingly, I did a quick and dirty analysis using pictures collected from Orchard Road area in Singapore. Why Orchard? Well, let’s just say because Orchard is one of the most frequented tourists spots in Singapore, which makes my analysis more representative.

I carried out analysis on the pictures collected in January-February months of 2014, 2015, and 2016. This makes comparison easier and more uniform. As the filters offered by Instagram changed over the 2 years period, I am not plotting all the filter counts for 3 years on the same graph. Instead I show you 3 separate graphs — one for each year. Also, I show bars on the graph only for filters which were used more than 500 times in the 2 months period. This is arbitrary but it helps me depict a meaningful bar graphs. All the filters with <= 500 pictures were combined and labeled “Other”, which will show up in the graphs.

Without further ado, here are the three graphs:

orchard2014orchard2015orchard2016

Well, I am not an outlier! It turns out that at least from 2014, people have been using Normal filter (basically no filter) more than any other filter. The percentages of pictures with Normal filter were 59% in 2014, 73% in 2015, and 65% in 2016.

It’s tough to say why people selected the filters they did. My hypothesis is that people are lazy and so they will go with the default. “Normal” filter is the default so it’s picked up the most often. Now Instagram has been changing the filters so I don’t know how they were arranged in 2014 or 2015. But for 2016, the ordering was as follows:

FullSizeRender 01FullSizeRender 02FullSizeRender 03FullSizeRender 04FullSizeRender 05FullSizeRender 06

Clarendon and Gingham are the next two filters shown by Instagram after Normal, which are also the next two most commonly used filters in Orchard area! After that, the filter ranking in the graph loses correlation with the Instagram’s  default ordering of filters. Perhaps, this indicates that non-lazy people actually hunt down the filter that gives them the best looking result. Still Juno and Lark, which are 5th and 6th on my 2016 graph, appear on 7th and 5th position in the Instagram ordering. Hudson, Sierra, and X-Pro II which are at the end on my bar graph, also appear in Instagram ordering towards the end. It seems that there is some support for the “lazy” hypothesis!

If you have more to add, please share your insights in the comments.

How Fashion Brands Should Use Facebook

This post doesn’t list my opinions. Instead check out the embedded video below where Tracy Yaverbaun, Director of Retail, Luxury & Fashion Partnerships at Facebook shares her experiences. Start watching from 4 minutes mark.

Update: Watch it from 18 minutes mark for more relevant discussion on luxury and fashion

Summary of Lecture 3 – 16/08/2012

In the first half of today’s class, we had Wall Street Journal‘s business and technology journalist Lora Kolodny speaking with us on Skype from San Francisco. I know Lora because I subscribe to her Facebook updates and sometime participate in the discussion. Considering that she has written for big names as New York Times, Fast Company, Inc, and TechCrunch, it is a great surprise that she is so approachable!

I invited Lora to speak with our students on primarily two topics–the social media start-up scenario and advice on starting your own business. The call went on for about an hour so I won’t be able to cover everything we spoke about. However, here are a few takeaways from her talk-

1) Although social media companies are getting a beating in the stock market, VC interest in social media start-ups remains high.

2) Any new platform, service, etc. must have a clear mobile strategy.

3) Social media adoption in Asia is growing rapidly.

4) For new start-ups, it is essential to evaluate whether they need large investment. Further, creating a personal brand is critical to reach out to potential investors. She suggested joining newer platforms early to create a significant following. Lora has more than 110,000 subscribers on Facebook!

5) She suggested using services like YouNoodle to connect to other entrepreneurs.

My students could add more to this.

The second half of the session was devoted to discussing the ‘Honeycomb Framework’ for selecting and managing various social media channels. The paper is available for download from here and a case study from Australia is available here. Ian MacCarthy, one of the authors of this paper explains what they propose –

“We explain how a firm can recognize and understand its social media landscape, using the honeycomb framework; develop strategies that are congruent with, or suited to, different social media functionalities and the goals of the firm; develop curating strategies for their own social media interactions and content; and finally use the honeycomb structure as a tool to evaluate the constantly changing social media activity.”

Honeycomb framework identifies seven components of social media – identity, sharing, conversations, presence, relationships, reputation, and groups. The diagram below shows what each component means.

The framework give clear guidance to selecting a social media channel. As a business you need to decide what your community is doing and what the community members’ inherent motivations are. Accordingly, one can select the social media channel. For example, LinkedIn has ‘Identity’ as its clear functionality. I know there are a few users on LinkedIn who are anonymous! Yeah, I keep on getting add requests from such people. But what’s the chance that I will ever accept such a request? If one doesn’t reveal one’s identity on LinkedIn, it defeats the whole purpose of that social network!

Social networks may have multiple functionalities. Consider Twitter. Originally, Twitter was used for broadcasting the message–sharing on the go. Therefore, ‘Sharing’ was its core functionality. However, these days Twitter also acts as a very common conversational tool. Therefore, ‘Conversations’ is an added core functionality to Twitter. The readers should think about other channels such as Facebook, FourSquare, Pinterest, blogs, etc. to see how they fit into this framework.

Once a business identifies the channel, it can use the following diagram to operationalize the channel management. The implications can be different based on the functionality a channel offers. For example, for reputation management, one needs to do a lot of monitoring using tools such as Klout scores.

Overall, honeycomb framework is great for channel selection and community management.

In the last leg of the session, I tried to answer the question “why do people share?” I used ‘Unselfish Gene‘ article to show one perspective. We know for a long time that the classic game ‘prisoner’s dilemma‘ doesn’t always end up with everyone choosing the game-theoretical solution. In other words people don’t like to betray others easily. Reputational concerns aside, human values are equally important in sharing something for the community’s good. Unselfish Gene tries to bring home that point.

Summary of Lecture 2 – Part 2, 14/08/2012

In part 1 of the summary, I briefly discussed the case study on SAP. In this part I will focus on 5 Cs of social media – community, conversations, content, channels, and collaboration (co-creation).

Before I describe the 5 Cs, I should clarify that these 5 elements of social media are neither original nor all-encompassing. There are, of course, several other aspects of social media strategy that one should take into account. However, as a guideline these five suffice in most cases.

There isn’t a clearcut mapping from the traditional 4 Ps of marketing–product, price, promotion, and place (distribution)–to the 5 Cs of social media marketing. Social media marketing gives a lot more importance to the community. It is partly because in many cases a community is already in existence and the businesses want to join it. This differs from the traditional “segmentation analysis.” A community is not a segment with characteristics of its members statistically identified by a marketer. Instead a community is a much more cohesive group of individuals who have some common intrinsic motivation for being a part of the community. Such communities can be described just by this motivation and nothing else. No other identifying characteristic may be attributed to them. For example, the popular financial blog www.zerohedge.com is an example of a completely anonymous community. Most of the blog posts are written under the pseudonym ‘Tyler Durden’–the unforgettable and legendary ‘Fight Club’ community leader played by Brad Pitt in the movie Fight Club. (If you haven’t watched this movie, the only advice I can give you is “Stop reading this blog and watch Fight Club, now!”) I was never an active member of Zero Hedge but I used to read their posts and the comments by members very regularly. During the financial crisis of 2008-2009, we were all driven by the same motivation–to read about and discuss the corruption on Wall Street and the dirty nexus between the banks, government officials, and politicians in the USA. Beyond that there was nothing you could know about us. This underscores the problem faced by a traditional marketer in the digital world.

A risky solution is to create your own community. That’s what SAP did. It’s risky because you would never know whether it will capture the attention of your target members, whether they will participate, engage, and contribute, and whether they will spread the word to grow your community. It takes a lot of time and effort (and also a great bit of luck) to organize and manage a successful online community.

The next 4 Cs–conversations, content, channels, and collaboration–will be discussed in detail as we progress in the course. Conversations are a must in social media marketing. The question is how you do it. There is always that temptation to get carried away and be condescending, witty, smart, and sometimes brutal because brands think that they are the leaders. But that’s the recipe for disaster. The conversations must be driven by empathy and honesty. In my opinion, these are the only two things that make conversations meaningful, thereby leading to long-lasting relationships.  Channels consist of different platforms and services on social media such as Facebook, Twitter, Youtube, and Foursquare. Again, I will talk more about this when in Lecture 5 and 6 we start working with the tools directly. Content is an essential part of social media marketing. In case of SAP, the content was the blogs by the developers and SAP employees, as well as the presentations created by SAP. They hold tremendous value for the community members. On August 23, we will dissect content strategy of an Indian business Ayojak in a case study (read the 4th abstract). Finally, collaboration (and co-creation) is the final component of social media strategy. More on this in lecture 3 summary. I had asked students to read ‘Unselfish Gene‘ and 1st chapter from book ‘Share This!

Composition of Corporate Social Media Team

I referred students to the survey results published by Altimeter. According to Altimeter, the typical size of a corporate social media team is 11 employees. Out of these 3 are the heart of the team–the community managers–who engage with customers. Their primary objectives are to create brand awareness, acquire customers, retain them, create the bran culture, and provide customer service. The social strategist, who is sitting at the top of the hierarchy, makes sure that the performance of the entire team is in line with the objectives set by top management. You can read more about the role of corporate social strategist here. The two guys on the left side of the chart, the education manager and the business unit liaison, hold inward looking positions. They chiefly interact with various business units internally, train people, and make sure that everyone uses a consistent strategy. Social media manager is in-charge of the operations. He/she decides the nature of interaction, gamification, what offers to provide, etc. Web developer is a part-time role and technical in nature. Finally, social analyst tracks various social media metrics. The last part of my course is focused on the metrics and crises management issues.

For a small business, 11 social media team members are meaningless. The suggestion from Altimeter is to use the proportions from their compositions. For example, is you want to devote 40 hours for social media in a week, roughly 11 hours (40 x 3/11) should be assigned to community management. Of course, if you hire one person it is impossible for that person to do everything. A person who is good at managing a community not necessarily will be good at doing analytics. A solution is to train your existing workforce to carry out part of these jobs. A person who is good with numbers could be trained to be social media analyst. Further, some of these functions could be automated or outsourced. You may not require an in-house web developer, for example.

Data: Composition of a Corporate Social Media Team

Social Media Dilemma of Luxury Brands

[This blog post is first of a series of posts I intend to write about social media for luxury brands. You can bookmark this post or subscribe to the blog to keep on getting regular updates]

In the last few months several luxury brands have started using social media more actively. I am getting to see this up and close due to ESSEC’s world-class MBA-Lux program. Our students have to work as strategy consultants for top notch luxury brands for 2-3 months before they graduate. I was supervising two such projects, which involved digital and social media strategies for two luxury brands. (I am not disclosing the names. The image of LVMH has nothing to do with these projects either.) In this post I am documenting a few observations from my experience in working on these projects.

Luxury brands have been ambivalent about joining social media. On one hand, social media gives them great visibility, opportunity to engage with their customers, and share the brand’s values with them. On the other hand, it exposes luxury brand to mass market, thereby overriding the exclusivity which defines luxury. In addition luxury brands are understandably more sensitive to reputational risks. As I have written earlier, social media also amplify the risk of brand dilution, something that no brand would like least of all luxury brands. It is therefore interesting to know how luxury brands have overcome this fear of social media.

I must admit that the managers at both the companies were extremely confident that they wanted to go digital route. In one case they were also confident that social media marketing was the way to go. Our students recommended using social media in either case. They gave a few great suggestions. The following two are my ex post recommendations –

1) In luxury business, social media are more about enhancing the experience of the consumers. This is a tough ask for current platforms. How can anyone create a seamless luxury experience on Facebook, Twitter, etc.? These platforms are for mass consumption. At the same time, many luxury buyers are already using these tools. One potential solution to overcome this problem is to create the luxury brand’s own social network, membership of which will be by invitation only. And while you are at it, why not create it for mobile usage? An app that is exclusively available to only a select few in itself is a great idea! This app will then link to common social networks. Imagine a luxury buyer sharing a picture of an LVMH purse visible only from this app to her friends on Facebook to get their feedback.

2) Try gamification because who doesn’t love rewards? It is an excellent way to keep customers engaged with your brand. Even luxury customers like to score some points, free gifts, or special treatment. Again a luxury retailer can introduce gamification in its own mobile app by tying up with FourSqaure. For example, a “Luxury Mayor” will get a special treatment every time he or she visits the outlet. The special treatment can be tailored to the previous purchases by the customer, thereby making it more relevant.

LVMH Champs Elysee, Paris