TheVigilante
Banned - Multiple Rules Violations
- Aug 31, 2010
- 14,993
- 16,105
One of the basic foundations of any SEO strategy is solid keyword research, which involves lots of time, effort and hours of patience.
Like Andy Chadwick, our keyword research sheets often exceed as much as 20k-50k keywords which we then try and segregate under different categories and sub-categories.
But is there any way to automate the process? Nothing can really replace human intelligence especially when it comes to keyword research but sure, there are parts that can be automated, saving you hours of time.
How? Andy figured out a way to do this using BigML, a freemium tool that helps you speed up your process of keyword categorization.
For most of us, the unpaid version of the tool should do the bulk of the work, unless you want multiple people working on it at the same time or want all available features.
So, what does the process look like?
+ Gathering the raw data: Andy takes an example of a clothing site to guide us through the process.
Source: https://searchengineland.com/how-to-use-machine-learning-if-you-cant-code-to-help-your-keyword-research-329912
Like Andy Chadwick, our keyword research sheets often exceed as much as 20k-50k keywords which we then try and segregate under different categories and sub-categories.
But is there any way to automate the process? Nothing can really replace human intelligence especially when it comes to keyword research but sure, there are parts that can be automated, saving you hours of time.
How? Andy figured out a way to do this using BigML, a freemium tool that helps you speed up your process of keyword categorization.
For most of us, the unpaid version of the tool should do the bulk of the work, unless you want multiple people working on it at the same time or want all available features.
So, what does the process look like?
+ Gathering the raw data: Andy takes an example of a clothing site to guide us through the process.
- He takes a few URLs from the site so he can group his keywords into categories and subcategories. To begin with, grab any of the URLs from the site and plug it into SEMrush.
- Filter by the top 20 keywords and export.
- Drop them into a spreadsheet and add the headings “category 1” and “category 2”.
- Repeat the same process for one of your competitor’s keywords ranking well.
- Export the keywords from SEMrush, add them to your sheet, drop the categories down and de-duplicate the list.
- Get rid of branded terms using a quick “Find and replace” tool.
- Save the above keyword file in CSV format and head to the BigML tool.
- Head to the sources tab and upload your training data.
- Once it’s loaded, click the file to open up the settings.
- Click the “configure data source” and ensure the categories are set to “categorical”.
- Close the “configure source” settings and click the “configure data set” button. Then deselect “category 2”.
- Rename the “dataset name” to something like ML Blog Data (Category 1) and click the “create dataset” button.
- Select your new data set in the “data sets” tab.
Source: https://searchengineland.com/how-to-use-machine-learning-if-you-cant-code-to-help-your-keyword-research-329912