This page shows the most significant words (tokens) in the corpus,
based on a supervised nonparametric trend detection algorithm originally
developed in the context of social media (Twitter). These results—shown on the right and
listed on the left below—suggest terms of potential
interest to the user based on their likelihood of embodying significant trends. In addtion,
we provide lists of top words based on simple counts, in the middle and right hand columns below.
Top 100 Words in Corpus
The raw count of words in the corpus.
Top 100 Words in Topics
The count of words that appear with high frequency in topics.