Is Social Media Worthy of Text Analytics?

Tom H.C. Anderson Misc 12 Comments

CokeSocialMediaAnalytics

Coke Says No Boost from Social Buzz – Should You Care?

 

Guess what, “Coca-Cola recently learned that Social Buzz doesn’t correlate with it’s short term sales”.

No Kidding – this shouldn’t really be a surprise to anyone, yet the value of both social media and social media monitoring is being debated as a result of this “news”.

Here’s how it works for those of you who don’t understand marketing, social media or analytics.

Social Media is a tactic – a tool. If you have a great advertising campaign wherever it is on TV and Social Media, just on TV, just on Social Media, whatever… then someone is probably likely to mention it on Twitter or blogs no matter how inconsequential to life your product is.

Conversely, if your advertising campaign sucks they are not likely to mention it much. Well unless it really sucks then a few might say that.

But so what, when it comes to predicting sales, monitoring tweets is at best looking for a trailing indicator – not the cause. Surely your sales numbers are a better indicator of your advertising success?

Social media certainly can and should play a critical role in most marketing campaigns today.

However, please, please realize that “Social Media Listening”, constitutes listening to mainly spam from the 8% of our population who tweets and blogs (while technically far more representative no one can analyze Facebook pages as they remain private/accessible only to Facebook).

Researchers, let’s keep things in perspective shall we. Way before we start discussing which approach to text analytics is most powerful we have to first decide what data is worthy of analysis. 140 character tweets from 8% of the population mainly trying to sell their “expertise” is just about the poorest form of data out there. Garbage In – Garbage Out!

The fact that Twitter even scores as many mentions as it does for products like “Coca-Cola”, which most regular consumers would be unlikely to ever think about any given week, is that there are so many want to be social media marketing guru’s on Twitter and blogs trying to analyze others marketing campaigns – further proving what a peculiar sample blogs and twitter is.

If you actually want to predict something like sales, you will need to first have a long serious think about what data, whether unstructured or structured, makes most sense in your model!

@TomHCAnderson

@OdinText

 

Comments 12

  1. Eugene Borisenko

    I think text analytics are better used to identify emerging trends or issues and then develop new marketing channels. Sabra Dipping Co. saw increased correlation in mentions between hummus and wine over a period of one year, which prompted the brand to engage with wine bloggers and run promotions at wine tasting events.

    1. Justin Wyman

      Totally agree. The value of the data is more often in figuring out the lifestyle of the consumers than their perception of brands.

  2. Casey

    You make a really important point here: what is social media data representative of? The hunger for data regardless of source has yielded a lot of data independent of its context. As well as we intuitively understand that a conversation with selected people in a given location and time cannot be swapped easily for another conversation with different people at a different time and location, we somehow expect social media data to be consistent, regardless of context.

    But does this mean that the data is useless? No. It just means that its use has to be considered much more carefully than it has been to date.

  3. Meta Brown

    Tom,

    You’ll get no quibble from me about the limitations of using twitter buzz as a predictor of product sales. But there is more than that to social media, and there are other applications for text analytics than predicting sales.

    One example: here in Chicago, we’ve had a problem with groups of people committing acts of theft and violence in our Magnificent Mile shopping area. Social media was used as a communication tool for organizing these crimes. Those messages are leading indicators, and it would be a worthy application for text analytics to identify them in real time, so that crime could be prevented.

  4. Post
    Author
    admin

    @Meta, Please don’t use the term “social media” to identify a data source, it is way too broad.

    Where specifically would the data come from? Twitter and Blogs??

  5. Dan

    Tom,

    Thanks for the article. You make some valid points here, but let’s not make the mistake of grouping all social media sites into one. There’s a huge divide in the way people mentally approach personal and professional social networks.

  6. Post
    Author
    admin

    @Dan I absolutely agree about not grouping multiple sources. That is why I would prefer people to stop using the term “social media monitoring” when what they are really talking about is “twitter and blog monitoring”.

    I don’t follow what you mean about professional networking, I assume you mean LinkedIn? But this too is not part of SMM

  7. Vernon

    So I guess I shouldn’t put my 401k into that Twitter-fueled hedge fund?

    But seriously, social media is what it is: yet another way for people to communicate with each other. i.e.,

    Letters > telephone > email > forums > SMS > IM and now, > social.

    Just like the communications media that came before it, there are obvious opportunities to *filter* social interactions to identify specific types of business opportunities in actionable business areas like: customer support, sharing content with people, customer prospecting, lead scoring & reputation management.

    But notice that all of these opportunities are best characterized as event- or person-specific.

    I think event-specific and person-specific data are where most of the value in mining social media data lies. Because you can actually use this type of information to make a sale, save a customer and get something done.

    Not to say that large-scale statistical analytics don’t offer some value. But IMO way too much hope and glory have been pinned on the magic of Big Social Data.

    People are finally waking up, thank goodness. Thanks for adding to the clarity.

  8. Pingback: “Is Social Media Worthy of Text Analytics”: A Response | Lexablog

  9. OdinText

    Good news is, I guess it doesn’t hurt to voice your discontent with the current state of affairs. Since this was written Coca-Cola has started using OdinText to do more advanced Next Gen Text Analytics with OdinText. http://staging.odintext.com/?p=1107

    It’ll be a journey, because any analytical tool is only as good as the data it gets, but Coca-Cola remains determined and we see them moving in new directions and making headway.

Leave a Reply

Your email address will not be published. Required fields are marked *