We know that unbrokered conversations about our brands, our
products, our services and our people are taking place among our
customers and prospects. Not knowing what's being said worries
us.
We fear the online backlash that virally spins out of control.
We're conscious of the hapless PR guy who sent out a press release
bragging about his Twitter account and who, 447 Diggs later, was
crowned "the biggest douche in social media." We watched JetBlue
get slammed and we are witnessing Toyota getting pilloried.
Twitter is potentially an early-warning radar for brands. By
monitoring the stream of 140 character missives, brands can ideally
get a feel for what's being said, understand competitive
comparisons, potentially identify brand loyalists or opinion-makers
worthy of extra care and attention and intervene before problems or
negative comments cascade into real trouble.
The two biggest outstanding issues are …
How do we effectively mine Twitter to reflect accurately what's
being said?
And what should brands do with the results?
PV
Kannan, CEO of 24/7Customer, a global call
center firm, has created a data-mining tool called 24/7Tweetview to
help clients monitor, mine and respond to customer sentiment in
near real-time. He claims to use "data mining and behavioral
analytics to analyze Twitter comments for sentiment, tone,
frequency and region" which in turn yields reports "for how the
company measures up against other businesses as well as within
their own customer base."
Working for typical call center clients - credit cards, telco
and cable companies, financial services firms, technology
manufacturers and retailers - this is a unique and differentiating
value proposition. PV and his guys create a snapshot of what's
going on based on 5 to 6 hours of data mining by rating sentiment
on a -1-0-+1 scale and by creating a "net emotion score" using a
combination of open source data mining tools and home made
analytical algorithms. They create keyword libraries for
their clients and focus on industry specific phrases (e.g. friends
and family) to assess competitive prices, offers, channels,
products and customer service issues.
The key to this effort and to the Twitter mining concept is
defining terms and setting the filters to collect, sort and assess
millions of conversations. At present everyone from PV to Radian6 to Dan Zarella does it their own
way.
If you doubt me, run a TweetPsych report on your own
Twitter account. Since my Twitter account is linked to my
blog, 85% of my tweets are professionally oriented. According to
TweetPsych, the language in my tweets indicates I post about
"learning" 73% more than average. But since I rarely write about
school or teaching this is a curious result. Similarly I write
consistently about media, yet this tool must be programmed for
different words ophrases since it indicates I tweet 17% less than
average about media.
The flattering, though bewildering stuff, is that I'm way below
average on anxiety (-34%) control (-54%), primordial reptilian
thoughts (-56%) and TMI or Self reference (-78%). You can see how
these entertaining but artificial categories are off to a degree
based on the unarticulated underlying programming assumptions.
But keep in mind that under the best circumstances with the best
tools (think NSA) we are unable to successfully mine jihadist
chatter or identify inbound would-be Nigerian bombers. Nobody has
really cracked the code on this yet. Marketers and social media
gurus are just getting started.
The next great leap will be to create common understandings
about how to analyze the Twitter stream. This will all just be
alchemy until the social media and marketing community
establish common definitions for tone, establish hypothetical
thresholds for frequency, discuss ways to measure intensity and put
forward best practices for weighing and reading the online tea
leaves.
And while there is some data and many apocryphal tales about
real-time customer service using Twitter to reverse bad service or
proactively delight customers, I suspect these are more random than
not.
Here are some of the outstanding questions I am sharing with
those who are working with me in attempting to monitor, measure and
respond to online conversations:
1. If Jeff Jarvis
tweets that your brand sucks. Is that better or worse than 50
unknown tweets explicitly or implicitly expressing anger,
disappointment, a sense of being ripped off or detailing service
shortfalls?
2. How do we weight intensity? It is specific language, overall
vehemence of the tweet or should it also account for resonance (was
it retweeted)?
3. How do we understand or process authority; some people
know much more than others or have experience or insights that
would give their opinion more credence or more weight?
4. If 50 or 100 of these tweets come thru over a week, a
month or a quarter, how serious should a brand take it and what
level of action or intervention is required? How much tweeting
action over what time period helps or hurts you?
5. How do we separate out frequent tweeters and
blabbermouths from thoughtful or opinion-leading tweeters?
6. Is frequency enough of an indicator. If not how can we
mine and measure the content of tweets?
7. How much negative feedback is enough to cause genuine
concern and prompt action? In highly transactional businesses
someone is always complaining. Assuming that every brand has a few
detractors, how much bad news or how many bad raps are necessary to
call out the customer service or PR firemen?
8. What is the interplay between brand advocates and
loyalists tweeting in opposition to detractors? Is there a
baseline balance of online commentary that brands should expect?
How much frequency or intensity is needed to prompt a specific
response? How do you know when you're really in trouble?
9. How do you weight tweets? And is it really in the best
interests of a brand to air or fix these situations in a public
forum or should brand tweets direct disgruntled customers
offline?
Few marketers doubt the ultimate value of Twitter and
other social media for uncovering customer sentiment and improving
customer engagement. But we are in the early pioneer days of
data-mining and everyone should be conscious that what we are
dredging up might or might not be a clear or accurate reflection of
what's really going on. For the near term --stay paranoid.
