Craig Bradford, VP of London for online marketing agency Distilled, has provided instructions on how to create a persona research in under 5 minutes that leverages cutting-edge IBM Artificial Intelligence technology – although it does take some time and effort to setup initially.
Bradford wanted to answer two pressing questions for marketers:
- What websites does my audience visits and spend time on?
- What topics are they interested in or reading on those sites?
This helps marketers find out what sites they should try to show up on, as well as what content would appeal to them.
The solution he came up with uses Followerwonk, Twitter, and IBM Watson’s Alchemy API to do top-level persona research very quickly.
Watson’s Alchemy API can do things a variety of things like language detection, sentiment analysis, and topic analysis. For the personas tool, it uses the “Concepts” feature that takes a block of text a URL, and creates a list of concepts that are relevant to the page. And it’s worth mentioning that Alchemy doesn’t just simply extract keywords, it can identify concepts that aren’t necessarily directly referenced in the text.
More detailed instructions are here, but this is be basic process:
- create a text file of the Twitter handles you want to research using Followerwonk;
- download Bradford’s code from Github;
- register a free Twitter API key and Alchemy API key, then create a file named api_keys.py with your details for Alchemy and Twitter;
- install Pip and the requirements file.
After all this is setup, you can run the script in the command line interface.
“Although it looks like a lot of steps, once you have this set up, it’s very easy to repeat,” Bradford notes. “Using this tool can get you some top-level persona information in a very short amount of time.”