Labels and Label Groups
What are labels?
Labels are words or phrases that categorize or describe entities within your site. For example: ‘red’, ‘Nike’ or ‘iPhone 14’
What’s the difference between labels and entities?
You might think, “hang on, these things look like named entities!” and you’d be right. Labels are a different name for entities, but they are subtly different.
Site Topic doesn’t have a list of pre-defined categories — entity names or label groups. Instead, it works these out as it turns keywords into labels. There are common ones that appear repeatedly, but Site Topic discovers these on the fly, then builds them into standardized structures.
NER is top-down and Site Topic is bottom-up. Both have their place. Site Topic’s approach is powerful because it allows us to structure messy demand data dynamically.
What are label groups?
Label groups are categories of these labels that relate to your site's theme. For example: ‘brand’, ‘colour’, ‘model’.
Why use labels and label groups?
Some keywords are ambiguous. Writing a keyword as a set of labels and label groups helps clarify the interpretation. For instance (keeping the fashion theme going), red valentino dress might be interpreted either as
colour:red,brand:valentino,category:dress,type:clothing- or as
brand:red valentino,category:dress,type:clothing
Interpreting or translating a keyword into labels and groups is an example of query understanding, a core part of search engine functionality.
Label and label groups let us group keywords meaningfully because they have universally understood names.
The "Top labels" view can optionally be seen with the keywords per label ("Top labels & keywords") or with the pages that rank for a label ("Top labels & pages").
Your top labels can be used to understand whether you miss facets or filters on your side. For instance, t's common that users will search for quite specific colors like nardo grey (for Audi cars) or navy blue, rather than the primary colors a site might typically use for filtering. Site Topic lets you work out how users intuitively think and search. It can make sense to add these as filters.
How do you recognise label variations in keywords?
Site Topic is able to recognise many variations in the way keywords are written. Examples of these are:
- Hierarchical label groups or taxonomies
- Keywords in which searchers implicitly expect a certain result, or implicit labels
- When there are multiple words to express the same thing, we use synonyms
- When people use TLAs and other ways to abbreviate. Site Topic needs to decode abbreviations and acronyms.