Let's look at an example of Hashtag Analytics in action.
I pulled data for five recent weeks. I used four weeks to segment users, and then I used one week to see if I could predict if there are folks out there who simply cannot help themselves by mentioning #nordstrom or Nordstrom or by re-tweeting messages from @nordstrom!
I identified 6,121 individuals who said something about #nordstrom/nordstrom/@nordstrom in my four week "pre" period.
- 85% only issued one tweet during the four week analysis period.
- 10% issued just two tweets during the four week analysis period.
Recall, I created a segment, called "Mega Participants". These are folks who tweeted in the last week, and tweeted in 3 or 4 of the past four weeks.
- 73 out of 6,121 participants were classified as "Mega Participants".
- 1.2% of the audience can be called "Mega Participants".
- 41.1% of Mega Participants engaged the following week.
- 3.1% of all other participants engaged the following week.
- 3.5% of all participants engaged the following week.
- Shaping The Conversation: 132 participants, 19.7% re-engagement rate.
- May Be Interested: 103 participants, 3.9% re-engagement rate.
- Making A Statement: 503 participants, 12.7% re-engagement rate.
- Dipping A Toe: 3,443 participants, 2.2% re-engagement rate.
- Joining The Conversation: 694 participants, 2.5% re-engagement rate.
- One Topic Experts: 806 participants, 2.0% re-engagement rate.
- Spreading The Word: 111 participants, 7.2% re-engagement rate.
- The Ignored: 329 participants, 1.8% re-engagement rate.
What does a "Dipping A Toe" participant look like? Here's one example from @amandalustbuser:
- John Mayer is playing in Nordstrom. This is a sign. I should buy everything.
- Having a shoe shopping black pump dilemma @nordstrom.
"May Be Interested" is a more engaged Digital Profile. Take a peek at a tweet that is somewhat representative of this audience, from a participant, and you'll see why.
- @nordstrom always carry a mirror. I've been to several cocktail parties where women have lipstick on their teeth.
- I got the @nordstrom job! I start my training for the lingerie dept on Monday.
It can be fun to review individual participants by Digital Profile. Let's profile a few of the participants.
First, here's @nordstrom, the corporate presence. During this four week stretch:
- 25 tweets.
- 4 statements.
- 8 retweets.
- 13 amplifications.
- 0 conversations (responses).
- 13 links.
- Re-tweeted 150 times by others.
- Answered 215 times by others.
- Digital Profile = Spreading The Word.
- 19 tweets.
- 8 statements.
- 4 retweets.
- 4 amplifications.
- 3 conversations (responses).
- 10 links.
- Re-tweeted 72 times by others.
- Answered 4 times by others.
- Digital Profile = Shaping The Conversation.
- 18 tweets.
- 6 statements.
- 9 retweets.
- 1 amplification.
- 3 conversations (responses).
- 6 links.
- Re-tweeted 45 times by others.
- Answered 14 times by others.
- Digital Profile = Joining The Conversation
There are participants who are highly engaged. There's @daliamacphee, for instance, a participant who is actively selling her merchandise, merchandise offered in Nordstrom stores.
- 158 tweets.
- 142 statements.
- 1 retweet.
- 8 amplifications.
- 7 conversations (responses).
- 150 links.
- Re-tweeted 12 times by others.
- Answered 5 times by others.
- Digital Profile = Making A Statement
- 24 tweets.
- 22 statements.
- 0 retweets.
- 0 amplifications.
- 2 conversations (responses).
- 12 links.
- Re-tweeted 0 times by others.
- Answered 1 times by others.
- Digital Profile = Making A Statement
How Does This Become Actionable?
By using Digital Profiles and by identifying Mega Participants, I can predict which participants are likely to be "engaged" next week. I simply maintain a database of all Twitter members engaged with @nordstrom, and i predict which participants are likely to be "engaged" next week. I feed my predictions back to you, the marketer, and you then tweet your message to your heart's content to the audience most likely to be engaged in the future.
In the case of Nordstrom, I identified more than 100 Twitter users who evangelize the brand. If I were at Nordstrom, I would communicate directly to this audience, as if they were part of my e-mail marketing list (to draw a parallel).
I realize this is big-company type work, and companies like Nordstrom are probably already compiling databases of Twitter evangelists, but it is worth sharing so that you can start thinking about how you apply Twitter to your Database Marketing initiatives.
Thanks a lot Kevin, great breakdown. I appreciate the time you put into this so that others could get an idea :)
ReplyDeleteKevin...
ReplyDeleteThis becomes actionable. Great. And I appreciate all your hard work here. But why is engagement even important in the context that we seem to be agreeing on? That is:
Identifying brand evangelists. And using database marketing to drive purchase behavior.
Is part II of the above context part of the picture? Said differently, how does knowing who these people are make a difference? What's the next step? Tweeting promotions and if so what's the business case reasoning behind doing so?
Thanks for considering.
Excellent insight as always Kevin. The link below has some useful ideas on automating data capture like this:
ReplyDeletehttp://blogs.sas.com/sasdummy/index.php?/archives/55-Mining-the-VP-debate-results-according-to-Twitter-with-SAS.html
Dave --- you've got to love that in the post you reference, the argument is about the code used to retrieve the data, and not about what to do with the data!
ReplyDeleteStep 1) Get food, step 2) Feast!
ReplyDeleteSome day you will have to explain to us how traditional marketing channels like email are cannibalized by facebook and twitter.
Measure it, Dave, your company has all of the resources in the world to measure it!
ReplyDeleteHi Jeff,
ReplyDeleteLet's go back to 2000. You had this new channel called "e-mail", it was a few years old.
People would ask, "what do you do with e-mail, send customers promotional messages, what's the business rational behind it?"
The average marketer will tweet their engaged customers promotional messages.
The database marketer takes a different view to the world. The database marketer uses information to segment customers, and to identify the appropriate marketing strategy.
For instance, in 2000, the e-mail database was separate from the customer database. In 2010, the e-mail database is fully integrated into the customer database. In catalog marketing, some customers buy from e-mail campaigns, so the catalog marketer cuts back on catalog mailings, saving a ton of money, but not sacrificing sales. In retail marketing, the e-mail address and the phone number are the tools that companies like Nordstrom use to have 1-to-1 relationships with customers. Store employees call best customers all of the time, inviting them into stores for events. Companies like Nordstrom measure sales per call or sales per e-mail campaign, they know the impact of having individual conversations with individual customers.
So the database marketer looks to integrate twitter ids within the customer database --- the database marketer integrates web analytics data and social media data and retail purchases and online purchases and advertising information. When the data is integrated, customers exhibit a channel preference, allowing the business to communicate in a cost-effective manner.
I have clients that use social channels and old school channels (i.e. calling customers on the phone or literally visiting the customer) to increase sales and significantly reduce traditional marketing expense.
In other words, the database marketer wants to capture all information about customers. Twitter is one of the few channels where the customer markets for you, so data integration is even that much more important here.
Hi, Kevin...
ReplyDeleteThanks for your thoughts. I appreciate the perspective and insight on your/the industry's intent. I don't always consider these things.
But I have to say. Since most people broadcast using Twitter (and do not have a reliable way to monitor Tweets... as they do email and telephone, etc.) they are not engaged. This is a bit myth. That's my viewpoint.
And I'm befuddled as to why the objective is to have customers evangalize (broadcast) using Twitter -- knowing the above is true... and knowing that advertising/attention is such a limited model in an interactive environment.
But I am open minded enough to consider that in some cases the "influencers"/evangelists actually exist. And appreciate your studying them, sharing data.
I mostly think this "influence the influencers" stuff is chasing a fantastically exciting theory espoused by gurus who've taken Malcom Gladwell's largely unproven (and successfully challenged) "Law of the Few" too far.
I'm a bigger believer that marketers are truly practicing Abraham Maslow's "law of the instrument" -- if the only tool we have is attention and "engagement" (largely undefined) might social media start looking like another nail?
Jeff, you might be right on every point.
ReplyDeleteIt doesn't mean you don't invent database marketing methodologies that may/may-not be relevant. You know how I feel about Social Media. And you know how I feel about Database Marketing. I'd rather try to innovate and create, and see what happens, than to just sit back and do nothing. I watched my field (catalogers) sit back and do nothing in 2000 when the rest of the world moved forward (or at least in a different direction), rendering the catalog marketer somewhat irrelevant. I'm not going to let that happen to me as a Database Marketer.
Since Google will remember this post and these comments forever, I thought it is important to note a couple of points for future readers.
ReplyDelete1 - I am not arguing whether engagement matters or not, in fact, I'm not really arguing whether it even exists or not. I am creating a framework for analyzing whether visitors/customers/engaged users/participants come back and act in a positive/negative way in the future. That's it.
2 - If you are in favor of engagement, or you are against it (and this goes to a lot of the feedback I've received via comments, Twitter, and e-mail in the past three days), stop arguing about it, go find data that either supports or counters your hypothesis, and then publish your findings for all to see. Both sides want to use clever words to form highly sophisticated opinions. I want to see data. Show me some data that supports or counters the argument. Publish data. I've attempted to start the process with this framework, now it is time for you to do something and to publish the results so that all can benefit.
3 - Not one person noticed that the Nordstrom audience was not engaged, while the Martha Stewart audience (in another post) was considerably more engaged. Nobody considered the pros/cons of the two audiences, the business models that cause the difference, and the most important fact ... nobody attempted to take this a step further and create a link between engagement or a lack of engagement and profit. It's as if few people actually read the findings ... either people wanted to applaud the methodology, criticize the methodology, or criticize the concept of engagement. As happens so often in the digital marketing world, there isn't a serious consideration of the underlying data and the causes/effects of the strategies that yield the data we analyze. This needs to improve.