How do you analyse social data?
It’s a simple enough question. But not a question simple enough to answer.
The specifics of the analysis change with each question being answered. The tool you use, the context of the analysis and the changes in language and imagery also make it difficult to have one clear approach to social data analysis.
There are quite a few moving parts that need to be considered and that makes it difficult to come back with an answer that’s suitable for everyone.
Now you’re probably thinking ‘why aren’t you giving me something more tangible to work with?
Good. That’s what we wanted to hear!
That’s why we’ve opened up our training vault to bring you a standard, repeatable and scalable process that you can use to answer any question with social data. In this long-read article, we introduce you to why the process you take is very important and talk you through each of the nine stages outlined.
JOIN THE LAB FOR FREE AND GET OUR HOW TO ANALYSE SOCIAL DATA WORKBOOK
Want to skip to the right section?
- Social Tools at the Ready
- What the Process Doesn’t Do
- The Kitchen Sink Analysis
- How to Analyse Social Data
- Stage 1: Define the Purpose
- Stage 2: Deconstructing Your Question
- Stage 3: Keywords and Phrases
- Stage 4: Create Your Query
- Stage 5: Develop Segmentation Criteria
- Stage 6: Unknown Segments
- Stage 7: Analysis
- Stage 8: Additional Analysis
- Stage 9: Interpretation
- What’s Next?
- Download the Social Data Analysis Workbook
Social Tools at the Ready
We’re starting with the elephant in the room: social tools.
The inevitable question is about the social tool you are using because – it’s the tool that gives you the insight.
What?! It’s not all about the social tool?
We think by now we all know that buying the latest social listening or social intelligence tool is only the first step in being able to generate actionable insights from social data. If you’re new to social data analysis you’ll learn this soon enough.
We’ve all watched the tool demos and seen how they manage to easily compile the insight you’re looking for. But when it comes to going it alone it’s always considerably more difficult and you’re left pulling our hair out, struggling to fathom out how the pros just conjured up something that’s good/makes sense.
You’re not alone, it’s happened to us too.
The tool that you are using is only the first step in a long process when generating actionable insight from social data. Let’s say that again… The tool that you are using is only the first step in a long process when generating actionable insight from social data.
If anyone else tells you otherwise run for the hills. Leave. And don’t go back. Ever.
When people see our work, this is the kind of thing we get back….
Hi @DrJillianNey , I think what you are doing is quite interesting. I am curious to find out the source of the data you analyze?
— Anisha Surana (@AnishaSurana) September 4, 2017
Everyone starts by asking about the tool we’re using. But what we’ve repeatedly found to be the most important thing in creating actionable insight are the steps you take when analysing the data.
The tool you are using and the functionality of this tool does ultimately dictate the approach you use to analyse the data. To put it simply, the tool you are using dictates the functional process of data analysis – how you segment the data for analysis. These tools are all a little different and you need to get used to their processes and their Boolean.
All that aside, there is a standard, logical process that you can use to analyse social data. This process brings you a level of rigour as well as a reputable process that is scalable. We use this process both working with private clients and when training new analysts.
What the Process Doesn’t Do…
It’s important to note that this process will not help you with:
- – Social media analytics or measurement when exploring interaction
- – Owned content analysis
This process is for when you want to analyse social media conversations to answer a question. When you want to analyse the context of the conversations relating to your brand or a topic.
The process that we’re about to share has been created to get you thinking more about the analysis you’re going to undertake. You’ll notice that there’s a lot of up front work before you even start to analyse the data.
The Kitchen Sink Analysis
If you rush in without a clear plan you’re likely to analyse everything and anything, it’s a scattergun approach. We call this a ‘Kitchen Sink Analysis’.
The Kitchen Sink Analysis is typically where most people start out. We know we did. But we quickly realised that it wasn’t giving us the best output.
We decided to stop analysing everything in the hope that we’d come up with some interesting insights and instead work through the problem.
The trouble with social data analysis is that you need to be logical when it comes to setting out the problem. Even for the best of us that can be tough.
The good news is that we’ve created a way to make it easy, fast and consistent.
How to Analyse Social Data
It’s important that you trust the process.
Trust. The. Process.
We know it seems long, but with this approach, you’ll get all of your thinking out of the way and have the framework to run the analysis from. This will make the final analysis easier, faster and more consistent.
Stage 1: Define the Purpose
First things first, you need to know:
- – The question you are trying to answer.
- – What you want to be able to do with the insight once you have it.
By doing so you lay the foundations and prepare yourself to focus on the data that matters, not the noise surrounding it.
The common questions I get asked to answer are:
- – What do people say about my brand?
- – How do people feel about my brand?
- – How can I sell more?
- – Who is my customer and how do they behave?
- – Can you help me win a pitch?
The common uses for the insight include:
- – Create a marketing campaign.
- – Create a content marketing ideas strategy.
- – Develop a new product or app.
- – Brand positioning.
- – Conversion rate optimisation.
Stage 2: Deconstructing Your Question
Now that you know what question it is that you want to answer and how you want to be able to use the insight, you’re ready to deconstruct your question.
This step is almost always skipped. It might be that people don’t realise that you need to go into this level of detail or maybe they feel that the data should guide their path.
Don’t fall into the trap.
What you want to do is to take your question and break it down into segments. This is extremely important because it helps you to break down the data into smaller, more specific parts that you can analyse properly.
To get actionable insights from social data you cannot rely on the ‘topics’, ‘trends’ or whatever the tool calls their automated ‘wordclouds’. This automation is generated through volume and you might miss the topic that’s important to you.
Just look at what a topic wordcloud says about ‘Green Bubbles’… Don’t use this automated ‘insight generator’, it really doesn’t give you insight.
Take the example of analysing music festival data. In this instance, you tend to find that it’s the performing artists that make up most of the chatter (between 60% and 90%). To us, it’s common sense that the artists will make up a lot of the talk, but it will skew your analysis.
Say that we want to understand the festival experience – we want to know about weather, camping, travel, food, drinks, toilets, other attendees, atmosphere, the “at home” experience and the “at festival” experience…
There are a lot of things that make up the festival experience that get completely drowned out by the talk about the artists. By deconstructing your question, you spend time thinking about the different elements that make up your larger question.
Stage 3: Keywords and Phrases
Now that you have the question and you’ve deconstructed it properly, you’re 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.
This includes all the hashtags, keywords, nicknames etc.
One of the things we do when we start working with a new client is to review their current tools and set up, along with their dashboards and other outputs. What we tend to find is that not enough time has been given to getting the keywords right.
You need to know how people [your audience] talk online. If you do not get the words and phrases right, you will never have all the data that you need.
To do this stage properly, go back and look at how you have deconstructed your question. Now 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.
For instance, we’ll look at reviews, forums and Twitter to understand more about language and the context around language.
Stage 4: Create Your Query
After you have all the phrases and keywords you can now start to construct your search query.
The biggest pitfall we 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 no good. Too little data won’t help.
For example, if you only have a brand name you will get everything about that brand. That’s fine if you are looking at brand equity but not if you only want to understand purchase intent.
And if you have too much data to work from you can easily stray back into a Kitchen Sink Analysis. Keep focused on the purpose of your analysis.
Query writing at a high level is complicated but it’s a skill that can be learned.
Ask your social listening tool for a bit of help if you get stuck.
Stage 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 in step 3.
Go back and start to create your segmentation queries.
The social tool you are using will have different terminology for what you are doing. For example, Brandwatch uses ‘rules and categories’ for this step, whereas Crimson Hexagon uses ‘quick filters’.
If you don’t do this step properly you will become reliant on the tools ‘volume automation’ and you’ll never get the insight you are looking for because it’s hidden.
Stage 6: Unknown Segments
Because social intelligence research is driven by naturally occurring social media conversations, you cannot account for every eventuality.
The process we’ve outlined will massively 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”.
The “unknown segments” are where we’ve found that the magic happens. They are the segments that you didn’t think about or know about. They are probably where the insight that you hadn’t considered is hiding.
Sometimes, absolute magic.
To do this you need to find the data that has not been segmented. The tool you are using will dictate how you go about this. Ask them for help.
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.
Remember, this is all down to language and if you’ve not thought of all the words and phrases properly you may miss some data. This is the stage where you refine what you have done before.
Stage 7: Analysis
We’re now finally ready for analysis.
Because you have segmented the data you’ll find the data easier to work with and analyse.
Remember, the question that you are trying to answer will dictate the analysis, not the other way round.
We advise looking for the context of the communication – discourse analysis on all the comments. You need to find out what the comments mean, the context around the keyword, and what it tells you about that segment of your ‘deconstructed’ question.
We talk more about this step in my interactive PDF and get you to map out your thinking…
JOIN THE LAB FOR FREE AND GET OUR HOW TO ANALYSE SOCIAL DATA WORKBOOK
Stage 8: Additional Analysis
There are other areas that have not been considered during the previous eight steps. For example, who is talking or where they are.
You might want to understand festival experiences from people in the UK compared to people in the USA or Australia.
Follow the same system but add in the extra segmentation. In this case demographics, psychographics or location. And, you’ll look to normalise the data across all relevant segments.
Stage 9: Interpretation
Your work doesn’t stop at analysis. Now you need to interpret what all this means!
We 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 a much easier job at this stage if you’ve worked through the process that we 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 analysed the data to find out the context driving the conversation – this lets you know the specifics.
This step is about putting all of this together and answering the original question. If we go back to the festival example we may be able to say how people prepare for rain and what they need from the festival site. We can say what type of food is desired and why, and so on.
There is an art to interpretation, but again, it is a skill that can be learned.
This is the overarching process that we use when analysing social data. There are other things we can do at each stage depending on the question we are answering and the metrics we use – this is done on a case by case basis.
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.
The next time you go to do any analysis follow the process… Don’t forget to download the PDF!
JOIN THE LAB FOR FREE AND GET OUR HOW TO ANALYSE SOCIAL DATA WORKBOOK
Want to share your social data analysis tips? Join The SI Lab for free and share your experiences!Join Now