from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
vectorizer = TfidfVectorizer(min_df=2, stop_words = 'english',\
strip_accents = 'unicode', lowercase=True, ngram_range=(1,2),\
norm='l2', smooth_idf=True, sublinear_tf=False, use_idf=True)
X = vectorizer.fit_transform(user_language_array)
D = -(X * X.T).todense() # Distance matrix: dot product between tfidf vectors