How to automatically identify tags (keywords) from a given text?

Question

It should behave like a Delicious toolbar for Firefox; it lists possible tags for a click. The effect is shown below:

The code should be able to find keywords for the text. Any good algorithm or open source project to recommend?

I found this post , but it is too general for my specific need.

Answer 1

I think you are looking for one of these answers,

• tag generation from text content
• How to extract common / meaningful phrases from a series of text entries
• tag generation from small text content (e.g. tweets)

In short - you are looking for extracting unigrams from text that somehow represent concepts within it - the method for this is called Pointwise Mutual Information, which is illustrated by an example in the first two links. Using the Python NLTK framework (which already has a bunch of built-in algorithms) may be your best starting point to work with.

Good luck