Your one-stop-shop to tag text data
When dealing with free text data, there is always a chance that one piece of text refers to a variety of topics. Identification of all these topics is an important step when transforming raw text data into insight.
The AI Tagging workflow comprises multiple steps designed in a way that you can:
- Extract topics with zero coding - the topics can then be used as tags/code frames
- Apply a human lens, modifying the extracted tags - i.e. relying on your knowledge of the field to generate the final tag list (i.e. code frame)
- Apply the final tags (i.e. code frames) to your dataset.
Relevance AI provides you with a great user interface for all the steps above. All you need to do is follow the setup wizard; zero coding is required!
This workflow extracts the topics from text data and allows you to finalize them based on your domain knowledge. Then tags are applied to the whole dataset. Results can be viewed on the Explorer App.
Note: Theme identification in tagging is of one-to-many grouping type.
This means all entries in a dataset are processed. Tags/code frames are extracted. Each entry is labelled with relevant tags/code frames based on conceptual similarity. For example:
Sydney's weather and landscape is amazing =>
tags = Sydney, weather, landscape
How to run AI Tagging
Apply AI Tagging to the data
Once you have uploaded your data, select your dataset and locate "AI Tagging" under workflows. If it is not listed in the Overview page (i.e. under "Suggested workflows for this dataset"), one easy way to access a workflow is to search for it under Browse Workflows as shown in the image below.
- As the first step in the setup, you will be asked to specify the text field you wish to analyze.
- Create the tag list or bring in an already saved tag list using Taxonomy Builder. Candidate tags will be shown on the page similar to the image below.
Note 1: Spending time on creating a good Taxonomy will save you a lot of time under Review and Refine steps.
Note 2: You can copy the values using the copy icon.
- Specify the maximum number of tags you expect to see per response.
- Define an alias for the current tagging experience. Aliases are useful when you wish to apply multiple tag sets to a single field.
- Optional settings:
- Receive an email notification upon workflow finalization
- You can apply filtering to your data and tag only a subset based on the existing values. For instance, tagging only where the NPS category is "detractor" or where Age is under 30.
- Apply to the whole dataset means if you wish to apply the workflow to your whole dataset or new items. When No is selected automatically all the untagged entries will be processed. So, it is mostly useful when you add entries to an existing dataset and wish to only process the new batch.
- Type in the survey question. For instance if the responses are answers to the question "What is your feedback on the service you received today?", type in the exact question.
Note 1: Suggestion (i.e. Suggest Tags under the taxonomy builder) is merely to extract some possible candidate tags, and does not label the dataset with any of the candidate tags. Labelling starts after clicking on Run workflow.
Note 2: Using the taxonomy builder and saving tag sets, you use tag sets between datasets.
After tagging starts you will see a progress bar and a "Review tagging results" button which gets activated when tagging is finalized.
Note 1: You do not need to keep the page open while the workflow is in progress. You can close the window or explore other functionalities of the platform.
Note 2: You can run multiple workflows in parallel (i.e. no need to wait for one to finalize).
Note 3: Workflow results are saved back to the dataset.
Note 4: Workflow results are independent of each other meaning they do not overwrite each other unless a workflow is run twice with the exact same workflow setup.
When AI-Tagging is finished, click on "Review tagging Results". This will open a new page where you can:
- see the tag list on the left and documents labeled with each tag on the right
- use search to list documents including a certain phrase
- Add new tags to a dataset
When presented with the tags and their corresponding documents, simply type in or copy paste new tags on the specified place on the top left. This will create a to-add list. Add as many tags as you have in mind, then click on
Apply changes. This will re-execute the tagging process on your dataset to apply the changes. Note that you can apply tag addition and removal. Have a look at tagging best practice guide
- Remove tags from a dataset
When presented with the tags and their corresponding documents, simply click on the
xnext to the tags you wish to remove. This will add them to the remove-list. Next, click on
Apply changes. This will re-execute the tagging process on your dataset to apply the changes. Note that you can apply tag addition and removal simultaneously.
In general and on average AI is 80 - 85% accurate. Relevance AI's Editor provides you with advanced options for reviewing and modifying tagging results.
Click on the "Refine in Category editor" to access Editor's Refine category responses page.
What is a good tag?
Is the tag precise?
This means that the tag properly conveys the intended topic and minimises opportunity for ambiguity. There are several ways that a tag can be not precise. For example:
- “Pricing / dollars, incl. deals”
- Could be split into 2 separate tags: “Pricing” and “Deals”
- “Convenience of Site” → “Close Proximity”
- "sydney" -> "Sydney" (Capital letters matter!) and similarly "Product Condition" -> "product condition" will help the AI
- "Shopping Experience" could instead be broken down into different components that make up the shopping experience such as "checkout experience", "parking lot", "friendly staff".
- “Pricing / dollars, incl. deals”
Is the tag concise?
This means that this is not an incredibly wordy tag. A tag should not have unnecessary words where possible as this can dilute meaning.
- “Good Customer Service” → “Customer Service” (unless you are specifically looking for the good component of the word. This is important because good customer service will not tag customer service but customer service will tag good customer service).
Updated 26 days ago