Problem $1\mathrm{.}4.$ Consider the query string and documents as below: All texts should be

converted to lowercase and tokenized by the whitespaces or punctuations.

$$ Query:$$covid vaping study$$

$$ Documents:$$ d$1$: $$Vaping teens and young adults up to seven times more likely to contract

COVID$-19,$ study finds.$$ d$2$: $$Jasper Landgraab is now a young adult, he is off to university to study fine

art.$$ d$3$: $$New study shows that vaping causes anxiety and depression.$$

Compute the relevancy score of each document by using the tf$.$idf scheme as defined

below.

$$ score$($q$,$di$)=$

$$ tf $=$log$(1+$ft$,$d$)$

$$ idf $=$ log

N

tf$.$idft,d

t in Q

$1+$dft

$+1,$

$1$

where ft$,$d is the raw frequency of the term in the document, dft is the document frequency

of the term, and N is the total number of documents.