9 Social Media Data Analysis Steps for Marketing Intelligence
By Jillian Ney on October 3rd 2017Read this article on our full site
Dr Jillian Ney shares her process for social data analysis, including nine steps that will see you from research question to report.
“I don’t have time for a fishing trip”.
This was the response from the Chief of Insight at a major insurance company, when asked about social media listening during a market research conference.
The statement doesn’t sit well with me.
And I’m thinking that it probably won’t sit well with you either.
But it does make me think about three potential things…
- That they have struggled to get usable insight from social data and deem social intelligence too costly to pursue as a research method because…
- They do not have a clear process or method to segment and analyze social data and…
- They have struggled to generate insight from the data because of the difficulty in interpreting the data.
Instead of thinking through the analysis people have a tendency to rush into it to ‘see what happens…’ Maybe you have done this yourself, I know I have.
Introducing the Kitchen Sink Analysis
The thing is that I quickly learned that by doing this it was the fast road to nowhere and a very big time-waster. I now call this approach the ‘Kitchen Sink Analysis’.
Why? Well, because you kinda throw the kitchen sink in to find everything and anything that you can.
Generally, what happens with this approach is that you find the ‘nice to know’ [the career-killing phrase of social listening people] or the common-sense insights.
Eventually, you end up feeling like the good folks at the above mentioned company – like you are going on a fishing trip and don’t know if you’ll come back with a ‘catch’.
But it doesn’t have to be that way.
A Universal Social Data Analysis Process
I’ve been analyzing social data for over ten years.
Throughout this experience, both with and without tools at my disposal, I had unknowingly followed a process.
It wasn’t until earlier this year that I audited my proposals and project output, that I noticed the distinct steps that I take for social data analysis in marketing intelligence.
This is the process I use with my own private clients and how I train my team to think about their analysis approach.
Now that process can be yours too.
Step 1: Define the purpose
We start with the question you are trying to answer and what you want to be able to do with the insight once you have it.
By answering these two purpose questions you lay the foundations of how to approach the analysis and what the insight needs to do. You prepare yourself to focus on the data that matters.
If you’ve been analyzing social data for a while then you’ll know that there is too much ‘white noise’.
This noise is a total distraction and pushes you into a kitchen sink analysis. To overcome this problem, define your goals.
Step 2: Deconstructing Your Question
With your two answers ready, you’re now all set to deconstruct your question.
Take your question and break it down into smaller segments. This is extremely important because it helps you to break down the data into smaller relevant parts that you can analyze properly.
Step 3: Keywords and Phrases
You are now ready to start getting the keywords, phrases and language.
We all know that social listening is dependent upon you creating a ‘search query’. This is the stage where we get all the information we need to make up our search and segmentation queries.
To do this stage properly, go back and look at how you have deconstructed your question. Spend time looking at the language around each of your areas and get all the keywords, phrases and everything else you need to gather the right data.
Step 4: Create Your Query
It’s now time to construct your search query. Query writing at a high level is complicated, but it is a skill that can be learned.
The biggest pitfall I see at this stage is that the search query is too loose. Go back to your original question and think about the best way you can gather the data to answer that question.
Too much data is confusing and it can easily lead you back down into a Kitchen Sink Analysis. Too little data won’t help.
Step 5: Develop Segmentation Criteria
Now that you have the search query written and the data pulling through your tool, you now need to start segmenting the data.
These segments are related to how you deconstructed your question in step 2 and the phrases and keywords you collected at step 3. Go back and start to create your segmentation queries.
If you don’t do this step properly you become reliant on ‘volume automation’ and you’ll never get the insight you are looking for because it’s hidden.
Step 6: Unknown Segments
As social intelligence research is driven by naturally occurring social media conversations, you cannot account for every eventuality.
The process I’ve outlined will help to prepare you, but you’ll always find a chunk of data that you’ve collected that doesn’t fit into any of your segmentation criteria. These are our unknown segments, where the magic happens.
They are the segments that you didn’t know about. They are probably where the insight that you hadn’t considered is hiding.
What you are looking for in this data is to find a pattern and create a new segment or change up the segmentation criteria in the segments you had already created.
Step 7: Analysis
We’re now finally ready for analysis.
Having segmented the data, it will now be easier to work with and analyze.
The question that you are trying to answer will dictate the analysis. I advise looking for the context of the communication – discourse analysis on all the comments.
I talk more about this step in my interactive PDF and get you to map out your thinking.
Step 8: Interpretation
Your work doesn’t stop at analysis, you need to interpret what this means.
I often see too many people putting easy to measure metrics in reports and trying to pass that off as insight. It is not insight.
You’ll have an easier job at this step if you have worked through the process that I have set out here. To explain…
- You know what you want to answer and what you need to do with the insight – this helps you to identify what is important in the final interpretation and report. You don’t measure the easy to get things, you prepare to answer the question properly.
- You’ve deconstructed the question and segmented the data properly – this lets you know the volume of conversation in each segment.
- You’ve analyzed the data to find out the context driving the conversation – this tells you the specifics.
This step is about putting all of this together and answering the original question.
Step 9: Additional Analysis
There are areas that have not been considered during the other eight steps that you can also explore.
For example, who is talking or their location.
Your immediate next step should be to review the searches and dashboards that you already have running, use this process to find out if you could be doing more and amend what you have accordingly.
If you want more inside tips on how I analyze social data, you can sign-up for my updates here. Or if you want to go deeper you can request an invite to my membership community here, use the code BW001.