It’s your turn to discover the nuances of social media research

Infographic on how Social Media are being used...

Image via Wikipedia

Remember the good old days when every offline study was parallel tested online? Remember all the headaches of changing baselines and bizzareness out of nowhere? The nature of data is that it doesn’t stay put even when you yell at it.

Social media research is the same. If you’re used to seeing results from online surveys a certain way, you will see shifts when you start doing social media research. Some of these shifts will fall into the bizarreness out of nowhere category. There is no way to explain where they came from and you will never be able to.

On the other hand, some differences will be very real. There are many reasons why.
• Your new dataset is comprised of people who’ve probably never been an active member of an online survey panel. Up until now, they’ve never been represented in research. They hung up on phone surveys and closed all the “Take survey now” pop-ups. These folks now have a voice.
• Your new data allows people to express themselves in a way never before permitted. Any topic, any tangent, any words, any slang, any rudeness. If people feel it is important enough to communicate it, it will be captured. Think of all the surveys, even the 60 minute surveys, that just weren’t long enough to capture that minute topic.
• Your new data is measured on a different scale. People are used to forcing their opinions into a box, whether it’s the “strongly agree” box or the “yes I do” box. Now, their words fit into an unlimited number of boxes and they don’t have to feel like they just can’t box their answer.

Don’t be afraid of different results. Embrace them as discovering nuances in your data. It’s a martha stewart good thing. Now have a warm homemade cookie.

Read these too

  • Check Out the Statistical Outlier on my LinkedIn Cluster Analysis
  • Why do surveys ask the same question 8 billion times?
  • How cool is market research? #mrx Social media research is the new one size fits all
  • How to upset me by generating leads with market research surveys
  • Data Tables: The scourge of falsely significant results #MRX
  • 1 topic 5 blogs: Embracing the evolution of listening
  • 3 responses

    1. Social comments and analytics for this post…

      This post was mentioned on Twitter by Netnoblography: “totally agree” 🙂 RT @LoveStats: It’s your turn to discover the nuances of social media research:

    2. Hi Annie, thank you for a warm homemade cookie. I am hungry…Great point. I understand now why traditional researchers hesitate to use SMR. It seems to me that SMR with real feelings could easier identify consumer insights than traditional research with pre-coded answers. I agree to Mr. Paul Banas comment on your last blog, ‘I’ve always thought of SMR as complimentary to other methods.’ After reading, I wondered if we could use SMR to test hypotheses which require the quantitative research. SMR is a method for making hypotheses or testing hypotheses or both in your view? I am afraid that I can make my point clear.

    3. Nice post Annie and agree with your overall premise. Clearly, different methods yields different results. Thus the need for ‘collaboration’ (or triangulation).

      I am a bit sceptical about the share of social media content generators (or ‘contributors’ to use the term you coined) that would not be represented in traditional surveys though. Indeed, I doubt that there are many “social media only” persona out there – on the contrary, the conversational nature of social media would allure me into believing that there’s some level of convergence between individual online survey responsiveness and social media engagement?

      Would be cool to see any research done that could shed further light on this.

      Cookies look good!

    %d bloggers like this: