The Beginner’s Guide to Using Natural Language Generation to Scale Content Marketing
You may have heard about the potential of artificial intelligence, machine learning, and related technologies.
Indeed they can improve marketing performance, productivity and personalization.
But getting started with these technologies isn’t always easy.
This post describes how to apply AI technologies to your marketing efforts.
In it, we’ll give you a 30,000-foot view of an AI technology called natural language generation (NLG) that is used by companies like the Associated Press to scale content creation.
Then, we’ll teach you how to get started with that technology today.
What Is AI and Why Should Marketers Care?
Artificial intelligence is the science of making machines smart.
Traditional marketing technology is built on algorithms that are told what to do by humans. With AI, the machine creates its own algorithms, determines new paths, and unlocks increased potential to advance marketing and business goals.
But “artificial intelligence” isn't just one thing.
It's a group of technologies, like machine learning, image recognition, deep learning, neural networks, natural language processing (NLP), and natural language generation (NLG).
Image Credit: Medium, John Koetsier
Each of these technologies can play a role in uncovering insights from massive datasets and achieving marketing and business goals using those insights.
And they’re used widely already today by companies like Amazon, Google, and Apple to power product recommendations, voice commands on your phone, online search, and much, much more.
What Is Natural Language Generation (NLG) and Why Should You Use It?
Natural language generation is just one of several artificial intelligence technologies.
Specifically, NLG produces text narratives from a structured dataset.
That means with the right data, an NLG program can automatically turn numbers in a spreadsheet into data-driven narratives.
It is related to, but distinct from, natural language processing (NLP), which analyzes text to uncover insights.
As put by NLG provider Narrative Science, “NLP reads while NLG writes.”
For instance, the Associated Press uses NLG to create its corporate earnings reports.
In the past, a human reporter spent time and energy reviewing earnings data and shaping it into a written report. Today, NLG “reads” the data and produces these narratives automatically in seconds, freeing up those reporters to pursue higher-value tasks within the organization.
Because the Associated Press earnings reports all follow a similar format, once NLG is set up, it can produce thousands of stories at scale.
The implications of NLG for content marketers are profound.
With properly structured data, marketers can use NLG to automate (at least partially) narratives that are based on data. Use cases might include analytics reports, data-driven blog posts, or product descriptions.
With the right data and a properly configured NLG template, you can leave some types of content creation to the machines while humans create other types of content and double down on promotion.
How Do You Get Started with NLG?
So how do marketers actually get started using NLG? Here are some initial steps to take.
1. Determine if you have a use case.
NLG isn’t for every content creation use case. As of writing, it would be essentially impossible to create the post you’re reading with NLG. This isn’t a data-driven narrative; it’s a unique creative output designed to answer a specific question.
Instead, look first to the stories you’re already manually telling with numbers. Think about "stories" as any narratives that make sense of data. This might include external-facing or internal-facing reports, summaries, fact sheets, etc.
Do you produce these types of stories regularly? Are any of these narratives in a consistent, repeatable formats (i.e. you’re reporting on or telling a story about the same types of numbers each week or month)? These might be candidates for NLG automation.
For instance, PR 20/20, the marketing agency behind the Marketing Artificial Intelligence Institute, has used NLG to cut down analysis and production time of Google Analytics reports by 80%.
2. Look at how your data is structured.
Even with a use case, NLG needs structured data to work.
Are your datasets organized in ordered columns and rows? Current NLG solutions will require a CSV upload, so data needs to be clean and relatively consistent to get value out of this technology.
Or, you may need to invest time into cleaning up your data before uploading it to an NLG system.
3. Be realistic about your ROI.
NLG solutions typically require substantial time to set up. You also need to pay for a solution, and likely related NLG services. You’ll want to take a realistic look at the technology, what it can do for you, and how much you can scale using it.
Start by analyzing how long reports, articles or narratives currently take, then see how much time NLG can potentially shave off.
Finally, apply those time savings to all staff whom NLG would affect. An hour saved per week per employee may make financial sense for your organization.
A Word of Warning Before You Start Using Natural Language Generation
It should be noted that natural language generation has some pitfalls.
This may raise justifiable fears about building operations or services on top of a solution that may dramatically change or disappear in the future. Marketers experimenting with NLG should pragmatically understand these concerns upfront as they analyze whether or not NLG can create value for their organizations.
Some large enterprises may choose to build their own NLG engines. For example, The Washington Post created Heliograf, and has used it to write stories for the Olympics and more than 500 races in 2016 elections in the United States.
About Mike Kaput
Mike Kaput is the Director of Marketing AI Institute and a senior consultant at PR 20/20. He writes and speaks about how marketers can understand, adopt, and pilot artificial intelligence to increase revenue and reduce costs. Full bio.