Q$4.$ Generate a sparse matrix using cosine$\_$similarity for the first $100$th tweets in this dataset.

$$ Q$5.$ Find the highest cosine similarity for the first $100$th tweets in this dataset.

$$ Q$6.$ Find the top $3$ words that are closest to 'France $-$ Paris $+$ Berlin' using word$2$vec.

$$ Q$7.$ Compute the document similarity $($Word Mover$$s Distance$)$ between the $100$th and $1,000$th tweets.

$$ Q$8.$ Remove stopwords before computing the document similarity $($Word Mover$$s Distance$)$ between the $100$th and $1,000$th tweets.