Retrieval & ranking
Semantic Similarity
How close two pieces of text are in meaning, measured by comparing their embeddings.
Semantic similarity is a measure of how close two pieces of text are in meaning, computed by comparing their vector embeddings rather than their words. It is what lets an engine decide that your passage answers a query even when the phrasing is completely different.
For content, semantic similarity shifts the target from matching keywords to matching meaning. Covering a concept thoroughly and clearly, including the natural language buyers use, makes your passages semantically close to a wider range of real queries than keyword stuffing ever could.
It also underpins topic clustering and internal linking: grouping and connecting content by meaning helps engines understand the shape of your coverage.
Related terms
Cosine Similarity
A score from -1 to 1 measuring how closely two vectors point in the same direction.
Vector Embedding
A list of numbers that encodes meaning so related content sits close in vector space.
Passage Embedding
A numeric vector that captures a passage's meaning so similar passages sit near each other.
Co-occurrence
How often two terms appear together in text, used to infer how related they are.
Semantic SEO
Optimizing around topics, meaning and entities rather than individual keywords.
Want to know where you stand in AI answers?
We’ll show you which engines cite you, and which don’t.
Get a free AI citation audit