This tool characterizes a set of documents by finding a latent set of topics. Each document has a characteristic proportion of topics, and each topic has a characteristic proportion of words. Also of interest are the correlations between topics, to see how they interrelate.

[How it works]


Number of topics

Only use the top words (not including dull words like "the","of", etc.)

You can also specify additional words to omit, or you can create your own list of words to look at.

Additional words to skip:


Only include these words:

Please note that it may take a few minutes to upload and process your data.