wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Feature Extraction Quiz (BoW & TF-IDF)

Total questions: 20

Worksheet time: 10mins

Name
Class
Date
1.

Which of the following best describes the Bag of Words (BoW) model?

a)

It captures the order of words in a sentence.

b)

It uses semantic relationships between words.

c)

It converts text into a vector based on word frequency.

d)

It reduces the dimensionality of feature vectors using PCA.

2.

Which technique assigns lower weights to common words like 'the' or 'is'?

a)

BoW

b)

TF

c)

TF-IDF

d)

One-hot encoding

3.

What does TF in TF-IDF stand for?

a)

Term Frequency

b)

Textual Frequency

c)

Total Frequency

d)

Token Frequency

4.

What is the purpose of IDF in TF-IDF?

a)

To normalize word frequencies

b)

To highlight frequent terms in the corpus

c)

To penalize terms that appear in many documents

d)

To tokenize the input text

5.

Which of the following is a limitation of BoW?

a)

It cannot be used for long documents.

b)

It is not applicable to English language.

c)

It ignores word order and context.

d)

It works only with numerical data.

6.

Which method could address the limitation of BoW by capturing phrases?

a)

Stemming

b)

N-grams

c)

Stopword removal

d)

Lemmatization

7.

Which of the following has the highest IDF value?

a)

A word that appears in every document

b)

A word that appears in no documents

c)

A word that appears in only one document

d)

A word that appears in half the documents

8.

TF-IDF is generally preferred over BoW because:

a)

It uses deep learning.

b)

It requires no preprocessing.

c)

It balances term frequency with document rarity.

d)

It captures the meaning of sentences.

9.

What does a TF-IDF score of zero mean?

a)

The term is very rare.

b)

The term does not appear in the document.

c)

The term appears in all documents.

d)

The term has no semantic meaning.

10.

Which component of TF-IDF varies depending on the document itself?

a)

Term Frequency

b)

Inverse Document Frequency

c)

Corpus size

d)

Document length

11.

Which technique represents each word with a binary 0 or 1?

a)

TF-IDF

b)

BoW

c)

Word2Vec

d)

One-hot encoding

12.

Which term in TF-IDF penalizes common words?

a)

TF

b)

IDF

c)

N-gram

d)

Token

13.

What is the main mathematical operation in computing IDF?

a)

Multiplication

b)

Subtraction

c)

Logarithm

d)

Division

14.

BoW creates a vector whose length equals to:

a)

Number of words in the document

b)

Number of documents in the corpus

c)

Total unique words in the corpus

d)

Total number of characters in the document

15.

Which of the following is most impacted by document length?

a)

TF

b)

IDF

c)

TF-IDF

d)

BoW

16.

In TF-IDF, the log base in IDF is usually:

a)

2

b)

10

c)

e

d)

Any positive base

17.

Why might you use stopword removal before applying BoW?

a)

To reduce document length

b)

To remove punctuation

c)

To eliminate common, less informative words

d)

To tokenize the text

18.

What is a major disadvantage of BoW in sentiment analysis?

a)

Cannot be used in English

b)

Fails to distinguish between opposite meanings like 'good' and 'not good'

c)

Requires labeled data

d)

Depends heavily on word embeddings

19.

Which step is NOT part of creating a BoW model?

a)

Tokenization

b)

Vectorization

c)

Synonym replacement

d)

Vocabulary building

20.

What happens to rare words in a TF-IDF representation?

a)

They are removed

b)

They get lower weights

c)

They get higher weights

d)

They are ignored