Feeds:
Posts
Comments

Archive for March 23rd, 2008

Observe this graph of Google search traffic by the remaining candidates.

Blue is Barack Obama, Red is Hillary Clinton, Orange is John McCain

Google Trends for Barack Obama

The spikes all correlate with voting days or the day after.

I have nothing profound to say other than it’s pretty interesting that the days when tons of people seek info is after the die is cast.  It reminds a lot of the behavior we see in retail and ecommerce – in many product categories people are more likely to visit a retailer website AFTER they have made a purchase (confirm value of purchase, sink deeper into buyers remorse..). Companies spend a ton of money figuring out why people abandon carts, which isn’t actually what’s going on.

~R

add to del.icio.us :: Add to Blinkslist :: add to furl :: Digg it :: add to ma.gnolia :: Stumble It! :: add to simpy :: seed the vine :: :: :: TailRank :: post to facebook

Read Full Post »

I received the following from a director of ad operations, Jeremy Jones, in response to yesterday’s post on collective behavior and the other day’s post on vertical media.  His remarks focus on the confusion over social networking advertising (both selling and buying).  I include the full remark here and an annotated remark below.

[Social networks/social sites] struggle with how to sell the concept to advertisers.  No one gets it, not even the sn sites themselves.

I had believed that social networking and behavioral targeting was just a fad.  That it will end up just being another tool in the arsenal once somebody actually figures it out.  I think it won’t really take off until someone develops a standard that everyone can follow.  Until then it’s just a mishmash of technologies and ideas that are just tangents of the same idea.  Being in the industry, we hear about every new concept of trying to aggregate behavior and bucketing those behaviors to try and create useful targeting.  It all revolves around collecting site behavior.  Some of the more interesting ones actually involve trying to apply psychological profiles and social classifications based on the user’s browsing behavior.

Is sn or bt about the consumers or the influencers?  Up to this point, anyone trying to use influencers has typically been exposed.  All those attempts at viral are quickly uncovered as manufactured.  It is true what they say that the internet is the world’s greatest laboratory.  The collective intelligence will typically uncover a insincere effort rather quickly.  SEO has generally been regarded as a good thing.  Even though it has been used by every advertiser to increase their influence.  It has ensured that any content worth knowing can be found.  But what about social networking and behavioral targeting?  The impact of social networking is just beginning to be felt.  So much personal data.  Will the collective eventually see this as a good thing or bad?  It’s influence will be far greater than SEO.  Will they approve of having their personal details used for the purposes of a more efficient marketing machine?  Can they do anything about it if they really wanted to?

One of the current problems with behavioral targeting is that no one has developed a method of success reporting.  What is a success metric for a bt campaign?  Advertisers are still using visits and clicks as success metrics.  Widgets is an interesting method.  It requires adoption by users, and once adopted, do they interact with your widget?  Consume it’s content, pass it along to friends?  Do friends adopt it without prompting?  It certainly opens up a whole new area of measurable behaviors that were never available before.  This gets back to the influencer vs the consumer.  How do you target the influencers?  Heck, how do you identify the influencers.  That, I believe is the tricky part.  The influencers are not a stable group.  They are never the same.  They can be an influencer one day, and an consumer the next.  If you could come up with a method for identifying the influencers for any advertiser then you would really have something.

I think this response underscores the general discomfort with media and advertising right now.  We have the technology to deliver interesting experiences and we collect a lot of data.  We simply don’t have a good enough technology/science of behavior that has left the ivory tower and trickled into business intelligence.

We focus too much on the “biological details”(e.g. who are the influencers, where’s the meme/viral agent/contagion, what is the makeup of the content, onbrand strategies) that we’re losing site of the behavior, in particular the social behavior.  We do not need to know much about the influencers to take advtange of influencer behavior (what are the behaviors, what are the schedules of reinforcement, what are the reinforcers), history (normative behavior, rule sets, discriminant stimulus) and the context of the influence (the environment, the websites, the office, the watercooler, the telephone…).

Here’s my direct response to Jeremy:

[Social networks/social sites] struggle with how to sell the concept to advertisers.  No one gets it, not even the sn sites themselves.

“It” needs definition.   The confusion may stem from unclear values and how to measure achievement of that value.  What do advertisers value?  Transactions?  Clicks? User data? Sales?  “Brand awareness”?  Being hip/cool?  Often advertisers use buying agents (agencies, buying teams, their uncle…), so the values are compounded.  The buying agent may value sticking to budget, being hip, being secure…   The confusion in measurement for media and advertising has partial roots in what the bigger financial market (venture capitalists, board members, stock market/shareholders, banks/lenders) value. Do the financiers value media footprint (eyeballs), transactional value (CPMs), advertising market ownership (spend share), loyalty (repeat spends, repeat users)?   When you look at the two value sets and try to assess whether the social networking sites fulfill any combination/which combination you find that social networks are out of whack with mainstream values.  Social networks drive huge footprints and user loyalty and are good at exposing users to brands/ideas/concepts. Social networks have yet to drive transactions or any offsite activity so most of the values to advertisers with the current advertiser approach cannot be fulfilled.

Don’t forget to add the set of rapidly changing distribution mechanisms (the APIs, social networking platforms, ad implements, publishing toolsets, scripting languages, AJAX vs FLASH vs Silverlight, the tracking systems…)

Thus confusion.

Resolution?  Experience.  That’s it.  Everyone will gain experience and we’ll integrate social networking advertising and not even notice because their will be some other “new thing” chewing up attention on blogs and at water coolers.

I had believed that social networking and behavioral targeting was just a fad.

A common response to an unknown stimulus.  Until you experience new methods enough, everything we don’t know about is a fad.

That it will end up just being another tool in the arsenal once somebody actually figures it out.  I think it won’t really take off until someone develops a standard that everyone can follow.  Until then it’s just a mishmash of technologies and ideas that are just tangents of the same idea.  Being in the industry, we hear about every new concept of trying to aggregate behavior and bucketing those behaviors to try and create useful targeting.  It all revolves around collecting site behavior.

Right, see my note above.

Some of the more interesting ones actually involve trying to apply psychological profiles and social classifications based on the user’s browsing behavior.

Pyschological profiles?  ugh.  It’s behavior that matters.  The psychology, in typical usuage, is a useless abstraction.  As a thought experiment, profile yourself.  What’s you profile?  Another experiement: Go to your amazon.com page – based on the products you’ve purchased and they recommend, what does it really say about you and can you do much to target yourself that you couldn’t do by matching like categorized products that get ok user reviews?

Behavior classifications based on schedules of reinforcement,with historical and contextual classification is the way to go.  Read up on schedules on reinforcement to understand the concept and how it might be applied to online advertising.  Basically, a publisher needs to understand rates of reinforcement and what schedules a user behaves under.  You can have the perfect product and a great message but if you miss a users schedule, they won’t buy.  Schedules can be:

  • buying schedules
  • reading schedules
  • relationship schedules
  • job schedules
  • cultural schedules
  • learning schedules

One topical example that might help understanding. Think about this years elections and why the candidates might be having more success with their platforms vs. in previous years.  The voters schedules are inline with some politicians message.  The context of economy, health care, unpopular war, social upheaval, housing issues are both on social schedules/cycles and personal cycles.   Certain politician presentation styles and stance on these issues fit better in the current schedules than others.

Your own schedules impact how you vote and how others might influence your vote.

I suppose you could say “timing is everything.”

Is sn or bt about the consumers or the influencers?  Up to this point, anyone trying to use influencers has typically been exposed.  All those attempts at viral are quickly uncovered as manufactured.  It is true what they say that the internet is the world’s greatest laboratory.  The collective intelligence will typically uncover a insincere effort rather quickly.

Is there a difference between consumers and influencers?  and does the exposition of that difference matter at all?

Authenticity and credibility are very much tied to values.  A manufactured attempt a buzz is usually the result of the manufacturing body not understanding the values of the consumers. Often agencies, marketers and publishers get the optics (the outside packaging) of a product or service but totally miss the utility. (hint: ipods are much more than music on the go with a nice digital store)

SEO has generally been regarded as a good thing.  Even though it has been used by every advertiser to increase their influence.  It has ensured that any content worth knowing can be found.

I suppose.  A sidenote: SEO was also a product of the search companies themselves to improve their own product.  The better content can be found the more useful the search engine.

But what about social networking and behavioral targeting?  The impact of social networking is just beginning to be felt.  So much personal data.  Will the collective eventually see this as a good thing or bad?

It’s neither good nor bad and will never be labeled as such.  It’s all about value.  You give all your professional data to LinkedIn and Monster because they help you get a job, you do not always share this information with your land lord because he might use it against you.  You give your friends names to Facebook because it helps you communicate.  You give google all of your search queries because it finds the info you need, but you’d never share your search query list with your girlfriend – you’d have far too much explaining to do.

It’s influence will be far greater than SEO.  Will they approve of having their personal details used for the purposes of a more efficient marketing machine?  Can they do anything about it if they really wanted to?

Social networking traffic is different than search traffic.  It’s not greater or lesser in any quantifiable sense, certainly not yet.

Yes, you can do something about your data.  Always.

One of the current problems with behavioral targeting is that no one has developed a method of success reporting.  What is a success metric for a bt campaign?  Advertisers are still using visits and clicks as success metrics.  Widgets is an interesting method.  It requires adoption by users, and once adopted, do they interact with your widget?  Consume it’s content, pass it along to friends?  Do friends adopt it without prompting?  It certainly opens up a whole new area of measurable behaviors that were never available before.

See my earlier notes on the confusion of values.

This gets back to the influencer vs the consumer.  How do you target the influencers?  Heck, how do you identify the influencers.  That, I believe is the tricky part.  The influencers are not a stable group.  They are never the same.  They can be an influencer one day, and an consumer the next.  If you could come up with a method for identifying the influencers for any advertiser then you would really have something.

My focus is on coming up with a way to track, analyze and respond to schedules.  If I know your schedules, I don’t need to know you.  Tracking schedules doesn’t require demographic studies or surveys or other intrusive methods.  I can use the behaviors you exhibit.  The web is excellent for this.

My point is that I can spend time classifying people into various categories by gender, “personality”, social status in an effort to predict behavior OR I can just observe the behavior and schedules and attend directly to that.

~R

add to del.icio.us :: Add to Blinkslist :: add to furl :: Digg it :: add to ma.gnolia :: Stumble It! :: add to simpy :: seed the vine :: :: :: TailRank :: post to facebook

Read Full Post »