Is there a way to group items based on a broader category (e.g., skittles and snickers get labeled as "candy")?

Question

I'm wondering if there is a way (specific package, process, etc.) of grouping items based on an overall category? For example, I'm looking at empty search results and want to see what category customers are most interested in.

Let's say I have a list of searched terms: skittles, laundry, snickers and detergent. I would want to group these items based on a broader category (i.e., skittles and snickers are "candy" and laundry and detergent would be "cleaners").

I've done some research on this and have seen similar (but not exact) ways of doing this (e.g., common keyword grouping using NLP) but not sure if something like this exists in the world when there isn't necessarily any commonality. Any help or direction would be greatly appreciated.

Answer 1

Update here: The best way to handle this scenario is to use pretrained word embeddings using something like Google's BERT algorithm as the first pass and then layer on another ML model that is specific to the use case.