Generate AI tags

Label your data using AI for tag extraction

What are tags?

Tags (or what are sometimes called labels or code-frames) are simply keywords or keyphrases strongly related to an item (e.g. a comment, a description, etc.).

For instance, Australia, travel and nature are good tags/labels/code-frames for I travelled to Australia last summer and enjoyed the amazing nature.

Applying tags/labels/code-frames to items in a dataset is referred to as tagging. It is useful in many ways such as categorising items existing in a dataset.

Generate AI tags

Relevance AI's "Generate AI Tags" workflow helps you tag (i.e. apply a coding frame) to your dataset. This workflow uses strong natural language processing techniques to extract the tags / code frames from your dataset automatically.

Note 1: Depending on the size of the dataset, the initial step of automatically extracting the tag list could take rather long (i.e. about an hour).

Note 2: Relevance AI provides you with another workflow called Guided Tagging where you can supervise and modify the selected tag list according to your domain knowledge before tagging is applied to your dataset.

How to create AI tags on Relevance AI's platform

Once you have uploaded your data,

  1. Select your dataset and from the menu on the left-hand side, select "Generate AI Tags" under workflows. If it is not shown on the menu, click on view all and find "Create AI Tags".
Relevance AI - Access to "Create AI Tags" workflow

Relevance AI - Access to "Create AI Tags" workflow

  1. Follow the steps by:
  • Specifying which text field in your dataset should be used for automatically extracting the tag list (i.e. all label candidates for the whole dataset). Then click on continue. We used the Description text field in our dataset.
Relevance AI - Create AI tags setup - Selece a field

Relevance AI - Create AI tags setup - Selece a field

Relevance AI - Create AI tags setup - Selece a field

Relevance AI - Create AI tags setup - Selece a field

  • Enter a name for the field in which the tagging result is saved (i.e. a new field is going to be added to your dataset storing the tags assigned to each survey comment/document) and click on continue. In this example we used description_ai_tag as the field name.
Relevance AI - Create AI tags setup - Type in the name of the field in which the results should be saved

Relevance AI - Create AI tags setup - Type in the name of the field in which the results should be saved

  • And finally run the workflow by clicking on Run on the Cloud
Relevance AI - Create AI tags setup - Run/Activate the workflow

Relevance AI - Create AI tags setup - Run/Activate the workflow

You can see the state of the task in a table that pops open. When the task is marked as Completed go to the dataset and there you can see the new field containing the tags per document is added to your original data.

Relevance AI - Workflow status table

Relevance AI - Workflow status table

Note: After running this workflow, you can run Guided Tagging workflow. Here a user can apply their domain knowledge to supervise and modify the tag list (tag word/phrase candidates) before actually applying the tags to the dataset.

Note: In many cases incorporating one's domain knowledge improves the tagging results. After extracting tags using Relevance AI's "Create AI tags" workflow, you can use "Guided tagging" in which you are provided with the opportunity to monitor and modify the list of tags/code frames before actually applying them to your dataset.