How to Remove Common Words

When Sumupr analyses content, it removes the most common words in the English language before identifying the keywords. This is essential, otherwise the keywords would be words like ‘the’, ‘and’, and ‘a’.

Sumupr removes the top 100 lexemes, as identified by Oxford University Press. A lexeme is a group of words which share the same meaning, but applied in different contexts (e.g. past tense vs present tense). So the top 100 lexemes actually consists of far more than 100 words. By removing these lexemes, the quality of the keyword results from Sumupr is greatly improved.

If you want to include the most common words in your keyword results, click on the gear icon and deselect ‘Hide common words’.