Comments
8/18 Chat on social media analytics, 2 p.m. ET
You must login to participate in this chat. Please login.

Thanks, Pierre, for the counterpoint on this, and thanks Shawn and Beth for having me!  This was a pleasure to delve into for A2.

Blogger

Thanks Joe, Shawn, and Beth

Blogger

I absolutely agree that this is not a broadly perfected application of the technology.  It does have presently useful, valuable application, however, and the usefulness and value of this kind of application will only increase as we use it and play with it more.

Blogger

and it's that daunting that needs to be better improved -- analytics is to help make better decisions faster. Not there, but we have hope for sure!

Blogger

Thanks, Joe, Pierre, Cordell, Beth. Great chat!

Blogger

Yes, sorry to miss the first half of it.

Blogger

Last parting shot. Makes sense. But the context, as Pierre says, seemds daunting

Blogger

This was a great chat

Blogger

On that note, it's 3:30, so, alas, it's about time I mosied along.

Blogger

Taking a cue from the study on Twitter predicting box office receipts (link: http://arxiv.org/pdf/1003.5699v1), you could do something similar to look to Tweet volume and sentiment pre-release and post-release.  The more buzz and the more positive -- especially after release (once people have been able to see, buy, and try), the better that product -- in our case, the toy -- will sell.

Blogger

But back to our toy idea. I know people love it and will buy iy how? Certainly I can count how many times it is mentioned in social media. But what if this turns out to be because people hat it?

Blogger

Customer surveys are rife with problems.  First, you have to convince people to take them.  Then, as John Barnes points out in a great piece from earlier this week, you have to try to make sure they're answering them honestly.  And even before all that, as I point out with an upcoming piece for A2 that should go up in the near future, you have to make sure that the survey is constructed so as to give you accurate and useful information.  Many companies simply don't know how to do that.

Blogger

I think those predictions and context really belong more the team that is examining the data and assigning predictive ability rather than the tool.

Blogger

Back to your example, which I find much more interesting, how would we read the sentiments about our theoretical toy in the marketplace?

Blogger

Yes, that's been done as well.

Blogger

This kind of research is far more valuable than, say, a customer survey.

Blogger

I recall in another study certain key words were given values, positive or negative.

Blogger

Additionally, it's not being leveraged to its full predictive ability.  Instead, consultants are telling executives like, "Oh, people like this!" "Oh, people DON'T like this."  But you can actually use this data on a much more sophisticated level to predict future events AND make decisions based upon those predictions.  If you know what toy is likely to sell best this holiday season, you can make intelligent decisions as to how to market your own competing toy, when to release it, and even what kind of competing toys to develop.

Blogger

Exactly. Marketers use this to measure what they call brand loyalty which often just means brand mention.

Blogger

For starters, some sentiment analysis solutions simply look for a few keywords associated with your brand name and place little to no emphasis on context.

Blogger

Ha! Still there is a viral quality to social media. Like one voice crying fire in a crowded theatre.

Blogger

@Shawn: Again, I think that's hubris of the individual.  If you think you can manipulate the stock market all by yourself on Twitter, e-mail me and let's figure out how to get rich. ;)

Blogger

The real problem with most linguistic sentiment analysis as applied to social media is that it often does not go far enough -- simply looking for cliches.

Blogger

To your first point about Tweets being unrelated to stock tips, understood. But theoretically you could game sentiment, stir dissent, create alarm, stimulate lack of calm...or the reverse, couldn't you?

Blogger

So there are two prongs here: How useful a took linguistic sentiment analysis is, and how useful a source social content is.

Blogger

Before that, one fund realized a greater than 15% return based entirely on linguistic sentiment analysis of business sources -- executives, press releases, etc..

Blogger

@Shawn: Although there was another study that specifically did look at stock-related Tweets.  That study, too, found that there was the ability to predict -- in that case, based upon sentiment and volume.

Blogger

@Shawn: That's irrelevant to what Derwent does.  They don't look at stock-specific Tweets.  They look at everyday Tweets by all sorts of people about all sorts of subject.  It's simply a matter of looking at general global sentiment.

Blogger

@Pierre: We can howl at the wind all day about how it shouldn't work, how stupid it is, and how there are all sorts of problems with it -- but time after time it's been proven by people who are way smarter than us.  That's not to say we shouldn't still keep doing what we can to look for hammer out the kinks, but there really is something here that can change the world.

Blogger

Is the argument here that attempts to manipulate sentiment, like the guys who plant false market tips or rumors, would simply be lost in the noise?

Blogger

Derwent analyzes a million Tweets each day (which is something like 10% of all Tweets each day, I think), calculates a sentiment score for each, and plugs it into their algorithm -- analyzing for calmness.

Blogger

@Joe I hear you, but it's the idea of making a impact that has spread. The concern is that while a good idea, there needs to be better ways to eliminate gaming that distorts. The measurement tools have not come along deep enough for the average business to discern well.  It's gerat that the dialogue has gotten started, but measurment capability needs more development.

Blogger

Well, there's the example we've talked a lot about, Derwent Capital Markets.  It's a hedge fund that is based upon a study that found that Tweets could be successfully used to predict the Dow -- even as much as six days in advance.

Blogger

In any case, I maintain that its hubris to think that one person, a thousand people, or even 100,000 people can manipulate global social media that much.

Blogger

Joe, maybe we should talk about some specifics here. There's certainly science behind this stuff. Care to give some examples?

Blogger

Anyways, I've got to head off now so wanted to say thanks for joining. But don't let me stop the conversation! Chat away for as long as you'd like. :-)

Blogger

@Pierre: There's a difference between buying a follow or Like, and buying advocacy.  The follower-buying services are baloney because all they give you is a number -- nothing else.  (In fact, social media consultant Elliott Volkman pointed out on Social Media Today (sorry, I don't have the link) how using follower-buying services can have a negative ROI.)

Blogger

I know there are a lot of good and valuable conversations taking place in the social media universe. But comparatively, I'm not so sure.

Blogger

To Pierre's point about fan/follower-buying, I think that's where much of my skepticism comes in. As a longtime journalist subjected to PR maneuverings all of sorts, I tend toward cynicism.

 

Blogger

I agree with you on that point, Joe. I probably come of as more negative on this subject than I really am. I simply think there are some caveats.

Blogger

Here is the link, by the way, on the Twitter issue that makes some people doubt the relevancy of this data. http://gawker.com/5826645/

Blogger

Or taking Shawn's thought further, what if those followers are bought? Many fan-buying and follower-buying services about, so how do we sort those out as being overbiased.

Blogger

@Shawn: And in any case, I maintain that the obstacles are no argument against working to overcome them.  :)

Blogger

@Shawn: For one thing, the technology is pretty good at weeding out the fakes.  There may be some concern about people posting from multiple accounts, but even if those don't all get weeded out, they're a drop in the bucket.

Blogger

Maybe inane is a better word. I don't think any of us would argue about how much crap there is out there. 

Blogger

@Beth: I see them as no more arbitrary than any other communication, or any other human-influenced data set.  ;)

Blogger

Again, if a substantial portion of Newt Gingrich's Twitter followers, for example, don't exist, what does this say about our ability to read true public sentiment from Twitter?

Blogger

And disregard the seeming arbitrariness of social media communications? ;-)

 

Blogger

@Shawn: That's not an uncommon skepticism.  People are concerned that some may try to skew results.  At the same time, in the aggregate, considering the sheer volume of the millions and millions of Tweets, status updates, and what-have-you going up each day that are ripe for mining and analysis, any false indicators would likely be silenced.

Blogger

Like Neo in the Matrix, it is us who has to bend, not the spoon. We have to rethink are measurment tools and how we classify and quantify a statement, a remark, an idea.

Blogger

Shawn, these are measureable if planned and incorporated as part of a strategy initially. The challenge with social media is that many of the comments are spontaneous and require context to catagorize. That catagorization process differs in some ways as to how a javascript tag tracks a visits.  It requres a rethink. Not a bad idea, but a certain one. :-)

Blogger

I think the real problem people can't get around is whether these sentiments can be taken at face value or whether, for example, they can be gamed.

Blogger

Hi, Pierre, Shawn, and Beth!

Blogger

@Shawn: I think its use as a communications tool is precisely what makes it so valuable as a source of data.  It gets right into the hearts and minds of the public -- what they are saying and thinking when they're not interacting with you.  (The Onion tongue-in-cheek reported on what would happen if Google could listen to what you were saying on the phone.)

Blogger

Pierre. But again, all of this deals with measurable onlin behavior.

 

Blogger

Great question, Shawn. One is to discover what services/products are drawing customer interest. Another can be discovering content that a customer is searching for. A third can be determining which marketing is really eefctively drawing a good return on investment, be it through a brand lift or an actual sale.

Blogger

Hey Joe. Thanks for joining

Blogger

Hi, guys.  Sorry about the delay, but I'm here!

Blogger

Getting back to social media, I think a lot of us think of it as a communications tool, not a source of data.

 

Blogger

The technology has limits, but if managed well, it can reveal ideas and better decisions that can keep a company surviving the tough times.

Blogger

Pierre, if you were to lay out for a business owner what is possible to learn with online data, what would be on that list and of what value do you think it is to a company or organization?

Blogger

I think it's organizational more than anything. There are companies that sense that their website is important, but haven't realized that a consistent periodic analysis can lead to new ideas, improved customer service, and a way to weather the economic storm we have now.  It's not strategic to them, even though their data and analysis can be the ace in the deck that leads to innovation or new ways to market and brand a business.

Blogger

Pierre, so what's the reasoning for the separate data collections? Is this more of an organizational or technology issue?

Blogger

Beth, great question -- it's still separate in many cases. There's been studies from Experian and eMarketer that suggests that online behavior and offline behavior from consumers (and clients) are linked, that what you offer online affects whether or not you gain a sale.  Yet many businesses treat their web data as a seperate, even secondary consideration, when in fact it an be the canary in the coal mine that can warn you of an unmet customer need or sales influence.

Blogger

Very true Shawn.  Maybe the best approach is a brainstorm - capture and cleanse, since it it data, but withhold the judgement that requires a specific action. 

Blogger

Pierre, I'm curious -- from what you've seen out there, how successful are companies in integrating the data they're collecting from the web into some sort of master data repository? is this common, or do companies tend to keep their online data separate from data they collect from other sources?

Blogger

I also like the point Cordell makesabout finding unexpected results or reactions. We might call this the "squeaky wheel" effect. But if not measured accurately this could cause knee jerk reactions to problems that might not be that serious being amplified by social media. 

Blogger

Shawn, I like that there is research going on to better understand the web. Maybe the best blend of man and machine? :-)

Blogger

So Pierre, if sentiment analysis isn't worth a ton of our marketing attention right now, what is? 

Blogger

Cordell, good point.

Blogger

If you offer a response, a coupon could be a great reminder of other offerings to try, but all in all there should be something offered.

Blogger

Well, Pierre, the Stanford research focuses more on determining users with the greatest influence and predicting where to place a message so that it spreads virally. Here's the link to my post http://www.allanalytics.com/author.asp?section_id=1412&doc_id=232460& and to the Webinar http://scpd.stanford.edu/search/publicCourseSearchDetails.do?method=load&courseId=10842293

Blogger

Beth I agree. And just because it's not reliably representative doesn't mean it's not valueable.  Rather than looking for something that points to a broad sentiment maybe it's more useful for spotting things like oversights or gauging reactions you didn't expect.  Outliers so to speak.

Blogger

True, it can lead to a replacement, but again, a company must be careful.  When Honda's fanbase express their dislike for the Crosstour, the moderates tried unsuccessfully to focus the group on the vehicle's benefits - the way they did it made the fans feel as if they were not being heard...

Blogger

Sticking with that butter pecan example for a sec -- even if the company decides it's not financially in its best interest to relaunch the flavor, it at least can think about how to make those irked customers feel better about it -- sending a coupon for a new flavor, for example (and of course measuring the success of said campaign and modifying it as needed)

Blogger

Cordell. Awesome. Now that's the real value of Twitter. :)

 

Blogger

That behavior can be troubling if the ultimate decision to produce something or not is at stake

Blogger

Hi. Saw the twitter post and thought I'd check in.

Blogger

Well, the idea of predicting the strict likelihood of someone liking or not liking a site or linking to someone or not is a lot more about behavior (and measurable behavior) then trying to figure out how the user "feels."

Blogger

Beth, that can be a great point about vocal minority.  A lot of people may want Butter pecan, but if the margins are not profitable to produce it, it would be that a large number of people would economically justify its sale.  A minority may feel it, but not buy in enough quantity. 

Blogger

Pierre, I see. Shawn -- is that more to your point about what the Stanford guy is getting at?

Blogger

Hi, Cordell. Great to see you!

Blogger

But that sorting came from determining what to potentially respond and take action, which is missing with sentiment analysis, because context is needed to make the action or even imagine it.

Blogger

Don't you have a selection bias problem as well?  In the ice cream example, just because a bunch of people on FB launched a campaign to bring back Butter Pecan doesn't mean it's a widely held view.  Bringing it back may not be in thier best interest.

 

Blogger

The thing about comments is that you'll end up with a number of comments, but you need to sort the messages being given.  For car, no one eer said give me a cupholder -- there had been comments of needing more room, I'm in my car all day, but no one ever said my car needs a cupholder.  A cupholder is what the auto industry delivered after sorting through the comments...

Blogger

Pierre- to your point about Honda. That's thing, right -- if you're unhappy or disgruntled, you're more likely to voice your dismay. That's not necessarily the case if you're happy. Your voice becomes less important, so to speak, in that latter case.

Blogger

I recently attended a Webinar from Stanford University on the subject of data mining in the social media realm and wonder if this is not the best way to eventually gain real meaning from social media.

Blogger

The social media universe just seems so arbitrary to me, for the most part! But even so, I must admit to being intrigued by what researchers are trying to do with all this data amassing. Good to look in on rather than buy into at this point, though.

Blogger

Beth, It is. Many companies have run into it -- I recall Honda being noted for how FB commented on the Accord Crosstour were handle.  It is something to be noted, but the concern comes back to context and what can be done.  In the Honda example, the vehicle was already designed and being released, yet long-time Honda fans objected to it.  Honda still sold the vehicle. It's in production, and despite Honda's poor use of FB, they still had sales.  Sentiment may ahve been captured, but it did not lead to a significantly changed result.

Blogger

Credibility can be a problem if people do not see authentic interaction.  It become harder to attribute the context of a comment -- did it come from someone who had something to say or gaming the system?

Blogger

Pierre, hmmm. I'm thinking of something along the lines of noting that your FB fans -- customers -- are angry over product quality or some such. Recently I wrote abOUT OBERWEIS Dairy, which has an active FB community of users. What if a large portion express anger over the company's decision to discontinue Butter Pecan at the local ice cream shops. Isn't that type of sentiment worth noting and making actionable?

Blogger

The other objection you often hear is credibility because of people with multiple accounts and not using real names etc. Is that a realistic obstacle?

 

 

Blogger

Beth, I think the viability becomes a bit worse on a FB page -- to be analytic means to be actionable on an intent.  FB is popular, but it is harder to determine what to do once you've determine a score for it.  This is a main probvlem with FB Insights -- you have trending data, but it's not leading to a specific goal like you would see in a GA or Site Catalyst.

Blogger

Shawn, yes, the claims can be misleading, though I also think the core is that we have to change how we consider quantifying sentiment. An all encompassing score is somewhat helpful but is a byproduct of being "number one" at something, when in fact the idea should be more nuanced.

 

Blogger

I'm with you there. Of all the things to focus in on, and delegate dollars to, sentiment analysis would be love on priority list if I were a marketer. Too arbitrary in my mind -- at least when we think in terms of the general Twitter population. Does the viability change if you're dealing with a particular domain, though, such as your Facebook page for customers?

Blogger

So is it more what you view as the exaggerated claims that you object to than the possibility that this analysis may be possible in the future?

Blogger

And measurement is still linked to very basic web architecture that is changing due to how we engage the web.  It just makes measurement a tricky process that can be misinterpreted or over-emphasized without context.

Blogger

I think it's early in the game to declare sentiment analysis as being an answer to marketer's prayers. 

Many businesses are still struggling with interpretation of data and how to incorporate social media into a strategy at the get go.

Blogger

So, Pierre, you recently participated in our Point/Counterpoint debate on sentiment analysis. And you don't much care for it at this point. Why don't you summarize your concerns?

Blogger

Shall we get started and let people trickle in if they are so inclined?

 

Blogger

You to. Think we can get started and Joe can join us when he's able.

 

Blogger

Let's wait a few moments to see who all may join us.

Blogger

Hi Shawn! Great to chat with you!

Blogger

Hi Pierre. Glad you can join us. Joe may be running late.

Blogger

This is where we'll chat with Joe Stanganelli, social media consultant, and Pierre DeBois, Web analytics consultant, on social media analytics, including the pros and cons of sentiment analysis.   

Blogger


INFORMATION RESOURCES
ANALYTICS IN ACTION
CARTERTOONS
VIEW ALL +
QUICK POLL
VIEW ALL +