Posted by Darren Enta on Thu, Mar 18, 2010
A single incident on a single flight, one of several hundreds or thousands of flights scheduled on any day could potentially be deterimental to the public perception of an airline. Southwest Airlines recently discovered the importance of reputation management and how a quick response to an attack on their reputation via social networking is integral to offset the backlash created by a disgruntled passenger.
If you haven't heard the story on any major television network, read about it on
line or any printed publication, recently film director Kevin Smith encountered some difficulty while travelling from Oakland to Burbank. Smith, who by his own description considers himself "fat", purchased three return tickets for a convention he was attending. On his return to Burbank he was ejected from the plane citing safety regulations. Smith, renowned for his sharp wit as a screenplay writer did what most customers that have encountered unsatisfactory experiences do, he complained. Smith feeling rightfully humiliated and wrongfully ejected from a flight to which he had purchased three tickets took to his Twitter account and seemed to know the gravity of his actions posting: "You [messed] with the wrong sedentary processed-foods eater!"
Complaints and negative experiences are unavoidable in customer service and the impact of the complaint can be very different based on the situation. For example, if the manager of a restaurant knows that a food critic for a major publication is eating in his dinning room he is well aware that this particular customer's negative experience would be far more detrimental than that of other patrons. This is due to their ability to share their opinion with a much larger group of people than most would through the traditional means of word of mouth.
Southwest was very fortunate to have a diligent employee who was monitoring the company's Twitter account (over a weekend) and was able to negate some of the reputation attacks which proceeded to overwhelm the company's customer service department. Several customer service attempts to resolve the situation were posted on Twitter and attempts to contact Smith via his Twitter account which had become viral were noted by those who had joined in attacking Southwest's reputation on Smith's behalf. Several individuals following the incident went as far as defending Southwest and agreeing that Smith should have been removed from the plane while others commended Southwest's attempts at a providing a satisfactory resolution. Southwest's admirable attempts at a resolution were reported on Mashable.com.
The aftermath of this incident included Smith recording podcasts which were available on his website and through Apple's Itunes which millions have access to. A public apology was offered by Southwest airlines as well as an undisclosed amount of money spent to combat the negative publicity generated by this story.
Another interesting aspect of this incident was the documentation of the entire exchange between Southwest and Southwest supporters and Smith and Smith supporters for casual observers to view and formulate opinions regarding the handling of the situation. The lesson to be learned by any company that is reliant on its public reputation is that any customer now has the ability through social networking sites like Twitter, Facebook and Youtube to make a very public situation out of what was once a containable resolution....so make sure you are using a SMART social media monitoring tool!
Posted by Kevin Joy on Mon, Oct 19, 2009
Part 3 - Continued from...Social Media: The tip of the reputation management iceberg - Why the urgency?
Sweat the small stuff
When companies try to wrap their heads around internet reputation
management, they often focus on the criminal or potentially explosive stuff.
Make no mistake: Malware, phishing, counterfeiting, trademark and copyright
infractions, URL redirection, defamation and domain-based threats can all do
serious damage to your brand. Even one successful attack can permanently
destroy trust in your organization and drive away customers for good.
But danger also lurks in the unintentional or lesser forms
of threats, the kind of things that, even if not criminal in nature, can still
frustrate your customers and keep them from returning.
For example, do you actively and regularly review the links
on your organizational Web site to ensure they’re still valid? How about those
links into your website? Although they
should, most companies don’t. How about checking for uses of marks, images,
logos, etc. in 3rd party sites?
I often hear people say it’s too time-consuming, or that the pages where
they occur don’t rank high enough to worry about in search engines. That it’s too expensive and their people have
better things to do than repeatedly surf internet sites.
I’ll politely disagree: Every company needs to do this and
should, given how relatively simply this can be accomplished. If you had a
physical store, would you open it in the morning with products strewn randomly
on the floor? Or would you want to make sure everything is neatly where it
needs to be so shoppers can easily find what they’re looking for? And if you came across your logo or wares
being used in an unauthorized fashion, but in a far away place, wouldn’t you do
something about it if you could do so easily?
Your online presence deserves the same attention, because
visitors will abandon a site with broken links, preferring instead to spend
time on a competitor’s. Also, the long tail nature of Search Engine
Optimization (SEO) is such that even the more obscure terms are increasingly
important in driving qualified traffic.
Finally, traffic can be driven to less popular pages via links from more
popular ones, so why take the chance?
And that argument about not having enough time or budget to
do? Look at it this way: Do you know how much business a sub-optimal Web site
is costing you? It’s likely significantly more than any maintenance would cost.
And what about the cost of each lost visitor?
Or worse, what’s the cost of each “non-visitor”, those whose online
experience is such that they are either diverted away or negatively influenced
to the point of not seeking out your brand further? Services like ours can be cost effectively
deployed – allowing you to have the peace of mind that your site isn’t filled
with broken links, that SEO investments are being optimized, that your
customers aren’t being targeted for illicit activity and, in the process,
allowing your people to focus on what they do best.
Stay tuned for the final blog post in this series - Social Media: The tip of the reputation
management iceberg - Getting Started...
Posted by Elias Vamvakas on Thu, Oct 01, 2009
Part 2 - Continued from...
How do we at BrandProtect deal with Social Media Monitoring?
Financial success on the internet is all about traffic. In the old days Meta Tags where being used to "prop up" the importance of web sites. I am sure you remember that in the early days of the web, key words were being repeated over and over again to fool traffic engines, all for the sake of SEO (search engine optimization). Well, the Googles of the world got smarter and reduced the influence of those types of old SEO techniques, but the opportunity was too big to dismiss. Smart humans always find a way! The new way to fool search engines, techniques like embedding key words, phrases and even paragraphs invisibly amongst text had successfully tricked most search engines. This text can't be seen when you read a web page, but is picked up by the search engine robots and thus make their way into search results. In most cases they have nothing to do with the context of the article, but they are highly charged with emotion to fool a search engine and they can fool us as well.
To put this all in context, let me give you some real data. We decided to use Manulife Financial as a test case to determine the accuracy of the data and our analysis. We compared our machine scored data against human validated scoring (yes, we had our people read EVERY post) and here are the results.
I won't go into specifics of this search other than reporting the numbers so you can get a feel for the outcome and the magnitude of the issues.
- Our system performed multi-source searches which resulted in 182,000 URLs.
- A number of relevancy filters were applied to only Blogs and Forums content which brought the number down to 4,239 URLs.
- Then the system performed sentiment analysis on the content, identifying 1,244 URLs that contained 5,675 mentions that carried positive, negative or neutral sentiment. Note that neutral sentiment is different from marketing messages. The latter is of no value to the client because most likely they are the client's own write up.
- To assess the quality of the machine discovered sentimental mentions, the same 1,244 URLs were routed to the human tagging pipeline. Without knowing the machine identified mentions, the human analyst examined the entire thread to identify sentimental mentions.
- The machine discovered sentimental mentions and human identified mentions where then correlated to determine the machine accuracy.
- The statistics are shown in the chart below:
So...
10% of the mentions Identified had strong sentiment and were completely relevant to the study. They are "the needles" that we are trying to identify. Human and machine were in total agreement on the sentiment polarities.
74% where correctly identified as sentimentally neutral and therefore not significant (This is the Hay). Human and machine were in total agreement on the lack of sentiment in the content.
1% where incorrectly scored. Machine assessed the sentiment as positive while human said it is negative and vice versa, or machine said there is no sentiment and human identified sentiment and vice versa. That means a polarity error of 1%.
15% where scored with correct sentiment, but human analyst considered them not relevant to the study. Something had fooled the system! On further analysis, we discovered that these posts had embedded text or were primarily designed for SEO purposes.
As far as the industry is concerned the above statistics would be incredible. Our automated systems scored the data for sentiment with unprecedented accuracy. If you assume all of the irrelevant comments were mistakes made by the system, our accuracy rate would be an industry leading 84%. If you assume that all of the irrelevant posts were scored accurately, the accuracy rating would move up to an incredible 99%.
So why are we not satisfied?
The data that we would be prioritizing for our clients would be those that had sentiment, or everything except posts without sentiment.
Out of those, the gems would be 585 out of 1,463 (585+817+61) or 40%
So we now have the real reason that customers are dissatisfied!
An industry leading 84%-99% accuracy rate means that more than every other post that a customer reviews is irrelevant. Of course 1 in 2 is better than the 1 in over a thousand, which would be the case for unaided search.
We and the industry clearly have some work to do. All I can tell you at this point is "We're on it!" As we are currently testing new technological advancements in this area I will keep you posted on our new test results :)
Posted by Elias Vamvakas on Fri, Sep 25, 2009
Part 2 - Continued from....Understanding Social Media Discussion. Why are we getting inundated with Garbage?
Now that we understand the magnitude of the problem, let me tell you how we have dealt with it. Actually, let me tell you how we have transitioned over time to deal with what we have learned and where we think it's going.
Having understood early on that clients are looking for quality not quantity, we designed a process years ago that tried to be all-encompassing when receiving data, but only presented the nuggets of insight that we identified for our clients. In this process, we leveraged technologies and used human tagging and analysis to confirm sentiment and identify issues that we believed our clients cared about.
This is a real example of the process and the magnitude of the effort required to put together target reports.
While our technology did a significant amount of "distilling" the data continued to be overwhelming and the insights were only discovered through our human taggers and analysts. This process while achieving good results and satisfied clients had 2 limitations. The first being costs. Human tagging is obviously expensive and fairly slow. The most important limitation was that the human analysis was limited to the knowledge and experience of the individual doing the tagging. This process was deficient in that it was missing the industry and company knowledge that is embedded within the client.
Therefore, in recent research and development of our new process, we determined the following to be key elements:
- 1- Data had to be relevant and accurately classified for sentiment and Influence
- 2- The methodology had to identify "valuable data". (We define valuable data as discussion threads that when combined with Industry expertise or specific company knowledge will produce actionable insights)
- 3- The technology had to grow and improve over time with the injection of human insight. We wanted a system that would be able to increase in accuracy as data about the industry, the company, lingo, mannerisms and phraseology were identified.
Let me spend a couple of minutes on the importance of word taxonomy, so that you can understand this concept a little better.
If you are trying to analyze a stock whose performance is being criticized as "bad" or the CEO as "wicked", you would want to attribute a different sentiment class than if you were analyzing the performance of the latest rock star and their music among a teenage audience. That's an easy example, but it gets more complicated. If you are in the financial services sector and assessing sentiment of an insurance company you would need to know that "low" is negative if it is referring to earnings, but positive if they are referring to premium rate.
To accomplish the above 3 elements we have now designed our system to go through 5 distinct phases of analysis -
We were very excited about the process, the technology as a base platform, and the results. The platform worked incredibly well with targeted studies, however the results were not as good as we had hoped for undirected studies, something like "show me everything that people talk about us that I should be concerned with" .
I think you will find the "why?" fascinating. I will also go through some real life data and our research to demonstrate our findings, but first let me describe what we have discovered.
Stay tuned for the final part of the Blog - Social Media Monitoring is Complicated....