Tips To Improve Tag Accuracy and Granularity
Know your data
It always helps if you have an understanding of the data. The more you know the better you can refine the tags.
It is recommended to run some clustering experiments (i.e. breaking your data into multiple clusters (e.g. 20 clusters, 50 clusters, etc.), review the results on the Explorer dashboard to better understand the main themes existing in your dataset.
Use good tags / code frames
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.
For example:- “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).
Apply you knowledge of the domain and refine tagging results
AI takes care of 70 to 80 % of the work. Meaning the results need your supervision. It is highly recommended not to rush through preparing the final tag candidate list (i.e. under Taxonomy Builder or when forming the code-frames manually) or when the refine step to achieve more accurate tagging results.
Updated about 2 months ago