# Cosine Similarity

The **cosine similarity** between two vectors is a measure that calculates the cosine of the angle between them.

Cosine similarity focuses on the direction instead of magnitude which is helpful in NLP and sentiment analysis. Longer document can have same **theme **as short sentences.

Three different angle between two vectors:
i) 90 degree (Orthogonal): **NOT **similar or Independent
ii) Less than 90 degree: **Similar**
iii) Greater than 90 degree: **Opposite**

**Note:
***- Words and sentences should be converted to vectors to calculate cosine similarity
- Tools such as ***Word2Vec***, bag of words with either ***TF***(term frequency) or ***TF-IDF***(term frequency-inverse document frequency) can be used*

### Calculate Cosine Similarity using Scikit-learn

Last updated