How to Semi-Automatically Code Text Data

Introduction

This article describes how to go from raw text data:

To a state where the text responses have been semi-automatically categorized and can be used for further analysis:

Requirements

You will need a Text variable in order to perform manual coding. Text variables are represented by a small a next to the variable in the Data Sets tree:

Method 1 - Creating your own categories

1. Select the text variable that you would like to code.
2. From the toolbar, go to Anything > Advanced Analysis > Text Analysis > Semi-Automatic Categorization > Mutually Exclusive Categories OR Multiple Overlapping Categories > New. NOTE: the choice between Mutually Exclusive Categories (single response) or Multiple Overlapping Categories (multiple response) is based on the structure of your text data.
3. By default, Displayr automatically starts with two categories: Missing Data and New Category. You can rename New Category by right-clicking and selecting Rename.
4. Read through the data to create your own categories and add them to the existing category list on the right-hand side of the screen. To add new categories, on the right side of the screen right-click and select Add Category and providing a name for each new category.

Method 2 - Use the Suggest function

1. Select the text variable that you would like to code.
2. From the toolbar, go to Anything > Advanced Analysis > Text Analysis > Semi-Automatic Categorization > Mutually Exclusive Categories OR Multiple Overlapping Categories > New. NOTE: the choice between Mutually Exclusive Categories (single response) or Multiple Overlapping Categories (multiple response) is based on the structure of your text data.
3. By default, Displayr automatically starts with two categories: Missing Data and New Category. You can rename New Category by right-clicking and selecting Rename.
4. If you do not know what categories to create, update the Sort by: drop-down to Fuzzy match and press the Suggest button. It will take some time the first time you do this as Displayr builds models in the background.
5. Based on the results of the Suggest function, add new categories one at a time, right-click and select Add Category. In this example "Service" is a suggested category result:
6. Repeat Steps 4-5 as needed.

Perform Fuzzy sort

1. Update the Sort by: drop-down to Fuzzy match
2. Type the name of the first category that you wish to identify in the Fuzzy sort on box and press Sort now. Displayr will take some time to run the models and sort the items in the list according to their similarity to the term. In the screenshot below, I've done a fuzzy sort on the word "coverage". The orange bars show how similar the words are to the search term. You can see the orange bars become narrower in the screenshot below as results become less exact.

Categorizing text

1. Once you have identified the verbatim text responses to categorize, select one or multiple responses (using your Ctrl key).
2. Click on the category or categories you wish to use on the right side of the screen. Use your Ctrl key on your keyboard to select multiple categories, if you are coding multiple overlapping mentions.
3. OPTIONAL: If coding multiple overlapping mentions, press Categorize as. This will categorize the data into the selected categories and remove it from the list of all responses.
4. Once all coding assignments are complete, click the Save Categories button. A new variable will appear in your Data Sets tree with "Categorized" in the name:

   

See Also

How to Refine and Edit Text Categories After Categorization