Articles in this section

See more

How to Tidy Categories When Automatically Classifying Into an Item List

  • Updated
Follow

After you've run a List of Items automatic categorization, you may want to tweak and further improve the results. If you are working with a small list or only need a few tweaks with the results, you can use the Variant Suggestions within the output to revise the coding (Method - Use Variant Suggestions). Otherwise, it will be faster to use the Text Categorization tool to easily refine matching and manage categories (Method - Use the Text Categorization tool). This article covers how to review and use suggestions where the automatic categorization algorithms think that the data could potentially be tidied further:

mceclip0.png

The variant suggestions can be added automatically to further train and improve the automatic categorization:

mceclip0.png

Requirements

Method - Use Variant Suggestions

  1. Select your List of Items output on the Page.
  2. In Properties 26UI_ObjectInspector.png, click the arrow next to the Diagnostics section at the bottom of the output to expand it.
  3. You will see a Variant Suggestions section that contains suggested category variants. Copy the rows of variants by highlighting the suggestions with your mouse and pressing Ctrl+C to copy or right-clicking and selecting Copy.
  4. From Properties 26UI_ObjectInspector.png, go to Data > Required Categories > Edit required phrases and variants.
  5. A spreadsheet will pop up on your screen. Paste the variants using Ctrl+V into the spreadsheet, starting on row 2, like so:
    mceclip0.png
  6. Click OK.
  7. The automatic categorization output will recalculate and include the variants that were pasted in. You may want to review Diagnostics > Variant Suggestions to see if further improvements can be made.
  8. To save the categories to use in other analyses, from Properties 26UI_ObjectInspector.png, go to Data > Save Variable(s) > Categories.

NOTE: The variables created from this using Save Variable(s) > Categories may become invalid and need to be deleted and recreated if the output has changed, either due to the input text variable being modified or the input settings being modified.

Method - Use the Text Categorization tool

If you need to make a lot of modifications to revise the final list of items results, you can easily do these with the Text Categorization tool. To do so, you will need to save the List of Items results into new variable, use these to generate a QCodes file, then import this code frame into the Text Categorization tool.

  1. Click on the List of Items output and from Properties 26UI_ObjectInspector.png, go to Data > Save Variable(s) > Categories.
  2. Create a QCodes file, which maps responses to the item list for the Text Categorization tool, see the Create QCodes File article in the technical reference.
  3. Select the text variable that was used in the List of Items output then click + > Text Categorization to open the tool. 
  4. Select Multiple themes and import the QCodes file into the Text Categorization tool, see How to Reuse an Existing Categorization (Code Frame) in a Different Document.
  5. Now you can make edits to the item list and reclassify responses, if desired, see How to Refine and Edit Text Themes After Classification.

Next

How To Automatically Classify Unstructured Text Data Into an Entity List

Related articles