Semantic content analysis will disrupt marketing – for the better

The state of play

In the climate of the current ‘data boom’, audience targeting naturally takes precedence, with the majority (55%) of marketers saying ‘better use of data’ for audience targeting is their priority in 2019, according to Econsultancy.

It makes sense. On a daily basis, we’re faced with countless blogs, podcasts, speakers and everything in-between promising that if we perfectly optimise our targeting, our messaging will beat the daunting odds of the 0.9% CTR cited by WordStream. And so, we dedicate hours and hours every week to creating personas, hypothesising about audiences, segmenting users and running lengthy A/B tests to find the piece of content that our audience love. We add to our already-complex marketing stacks tools that tell us what messaging has been more successful, in order for us to optimise.

But when we do find that winner, do we know why it works? Do we know exactly what features caused the higher CTR? Do we know how we’re going to recreate it in our next campaign, to make it better, even?

This lack of knowledge – despite all the tools and techniques we use to offer insight – is what we at Datasine call the ‘black box’ because when it comes to understanding why, we are left in the dark. Just looking at results doesn’t give us the insight needed to truly understand content preferences in an actionable way.

Semantic content analysis

To crack open the black box, we need to start conducting in-depth semantic analysis of our content. Only then can we begin to truly understand why some content resonates and some doesn’t.

As experienced marketers, we come prepackaged with a deep understanding of – and fascination with – psychology and our audience, meaning we’ve already got the skills on paper to analyse our content. It’s simply a matter of breaking it down into parts. We’ll look at this in terms of images and text.

If you want to analyse your imagery, you can take all the image assets you’ve ever created and note down the particular elements you used in each, then check to see if there are any patterns which relate those choices to your ad performance.

For example:

• Did you use a photo of your product outdoors? Or in the showroom?
• Were people visible in the shot?
• What was the size of the text, and the colour of any overlays or CTAs?

It may even be worth inviting a panel to judge your images on the emotions that they evoke, or photographers to assess the quality and composition of the shot.

You can do the same for text content, approaching this by categorising how you describe your product or service. For example:

• Do you appeal to your product’s ease of use?
• Are you emphasising your innovative credentials?
• Do you use particularly casual – or formal – language?

With this process, we can see which types of content are receiving the most engagement. And we can use these features to keep creating great campaigns that we further optimise as our understanding of customer content preferences grows.

Scaling content analysis

If we have just a few campaigns on the go, content analysis is easier, but it gets harder as we scale. It stops being practical to expect humans to spend days, weeks, even months labelling what goes into each piece of content. Here’s where machine learning and artificial intelligence (AI) come to the rescue.

AI models can extract all of these elements in seconds by analysing image or text semantically to look at content like humans do. That way, we can cut back on lengthy, expensive A/B testing, and get rid of guesswork once and for all - a vision we at Datasine are working toward. Our AI platform Connect (formerly Pomegranate) automatically identifies the most effective content for your audience.

By embracing semantic content analysis and working collaboratively with AI, we can feel confident in understanding exactly what content is going to work before we hit send.