Why this tool is useful
Use cosine similarity for local document comparison when term frequency matters but longer text alone should not automatically dominate the score.
Text & List Tools · runs locally
Cosine Word-Frequency Similarity Calculator
Measure the angle between two normalized word-frequency vectors so repeated terms influence the resulting score.
Ready. Your working data stays in this browser.
How it works
The browser counts normalized Unicode word tokens, computes a sparse dot product and divides it by the product of both vector magnitudes.
Practical example
The sample vectors are [2,1] and [1,2], so their cosine similarity is 4/5, or 0.8.
Validation
The calculation is deterministic and explains validation errors instead of silently changing invalid input.
Privacy boundary
Input and output remain in this tab. Copy and download happen through browser APIs without a server upload.
Result passport
Every run reports its tool mode, timestamp and input/output size so transformed data can be audited.