1 to 3 months –
Less than 10 hrs/week –
CI need someone who know how to generate n-grams for all the words in a Document.
Be able to compare each sentence to every sentence and identify which have the most over lap based on term frequency,
I also want you to be able to calculate sentiment for the sentences.
Statistics is a plus
Rapid miner is a plus
understanding of the use of clustering is a plus
being a Linguist is a plus