4/15/25, 11:16 BUAL 5660 Final Exam |
AM
BUAL 5660 FINAL EXAM QUESTIONS AND ANSWERS WITH
VERIFIED SOLUTIONS GRADED A++
Leave the first rating
Save
Terms in this set (65)
Topic Modeling is a supervised learning False
method. (T/F)
Given the inverse document frequency c. The term HATE occurs rarely compared to the term LOVE in the set of
for two words (LOVE and HATE) below documents
from the same corpus, which of the
statements is true? Explanation: A higher inverse document frequency (IDF) indicates a less
Hint: IDF(t) = log(Total # doc / # doc with frequent term, while a lower IDF weight indicates a more frequent term
term t)
IDF for LOVE = 4
IDF for HATE = 6
a.None
b.The term LOVE occurs rarely compared
to the term HATE in the set of documents
c.The term HATE occurs rarely compared
to the term LOVE in the set of documents
The collection of documents, required for d. Corpus
text analysis is known as:
a.Lexicon
b. Stemming
c. Dictionary
d. Corpus
Which of the following steps is part of d. stemming
text data cleaning process?
a.mean absolute error
b. degree centrality
c. small world phenomenon
d. stemming
An example of unstructured data is_____. c. customer reviews
a.gender of customers
b. movie rating score
c. customer reviews
d. age information
In the process of sentiment analysis, the b. positive and negative words dictionaries
terms are assigned as positive or negative
using:
a.term by document matrix (TDM)
b. positive and negative words
dictionaries
c. topic modeling
d. stemming
1/
7
, 4/15/25, 11:16 BUAL 5660 Final Exam |
AM
In N-P Polarity Classification of Sentiment True
Analysis, the goal is to classify the
OPINION as falling under one of two
opposing sentiment polarities or locate
its position on the continuum between
these two polarities. in other words,
a
sentiment score of the opinion is
generated. (T/F)
In the table below, the sentiment (Positive False
or Negative) are at the review level
not the term level. (T/F) Explanation: this table shows the sentiment at the term level
Preprocessed doc | term | TF abs |
sentiment
"Great food.. | Great[POS(Sent.. | 1 |
Positive
"Great food.. | good[POS(Sent.. | 1 |
Positive
""Great food.. | basic[POS(Sent.. | 1 |
Positive
Sentiment analysis (using the positive and False
negative dictionaries as learning in class)
is a supervised machine learning
approach. (T/F)
Which of the following steps is a part of d. Stemming
text data cleaning process?
a.Lexicon
b. Mean Absolute Error
c. Sentiment
d. Stemming
Association rule mining/Market Basket True
Analysis is an unsupervised
machine learning technique. (T/F)
Given a transactional dataset containing d. Association Rule Mining/Market Basket Analysis
bakery products purchased by 1,000
customers, which of the following
methods is most appropriate to find 'how
many times a chocolate cupcake is
bought when a brownie and strawberry
muffin are bought together:
a.Decision Tree
b. Neural Network
c. K-means Clustering
d.Association Rule Mining/Market Basket
Analysis
2/
7
AM
BUAL 5660 FINAL EXAM QUESTIONS AND ANSWERS WITH
VERIFIED SOLUTIONS GRADED A++
Leave the first rating
Save
Terms in this set (65)
Topic Modeling is a supervised learning False
method. (T/F)
Given the inverse document frequency c. The term HATE occurs rarely compared to the term LOVE in the set of
for two words (LOVE and HATE) below documents
from the same corpus, which of the
statements is true? Explanation: A higher inverse document frequency (IDF) indicates a less
Hint: IDF(t) = log(Total # doc / # doc with frequent term, while a lower IDF weight indicates a more frequent term
term t)
IDF for LOVE = 4
IDF for HATE = 6
a.None
b.The term LOVE occurs rarely compared
to the term HATE in the set of documents
c.The term HATE occurs rarely compared
to the term LOVE in the set of documents
The collection of documents, required for d. Corpus
text analysis is known as:
a.Lexicon
b. Stemming
c. Dictionary
d. Corpus
Which of the following steps is part of d. stemming
text data cleaning process?
a.mean absolute error
b. degree centrality
c. small world phenomenon
d. stemming
An example of unstructured data is_____. c. customer reviews
a.gender of customers
b. movie rating score
c. customer reviews
d. age information
In the process of sentiment analysis, the b. positive and negative words dictionaries
terms are assigned as positive or negative
using:
a.term by document matrix (TDM)
b. positive and negative words
dictionaries
c. topic modeling
d. stemming
1/
7
, 4/15/25, 11:16 BUAL 5660 Final Exam |
AM
In N-P Polarity Classification of Sentiment True
Analysis, the goal is to classify the
OPINION as falling under one of two
opposing sentiment polarities or locate
its position on the continuum between
these two polarities. in other words,
a
sentiment score of the opinion is
generated. (T/F)
In the table below, the sentiment (Positive False
or Negative) are at the review level
not the term level. (T/F) Explanation: this table shows the sentiment at the term level
Preprocessed doc | term | TF abs |
sentiment
"Great food.. | Great[POS(Sent.. | 1 |
Positive
"Great food.. | good[POS(Sent.. | 1 |
Positive
""Great food.. | basic[POS(Sent.. | 1 |
Positive
Sentiment analysis (using the positive and False
negative dictionaries as learning in class)
is a supervised machine learning
approach. (T/F)
Which of the following steps is a part of d. Stemming
text data cleaning process?
a.Lexicon
b. Mean Absolute Error
c. Sentiment
d. Stemming
Association rule mining/Market Basket True
Analysis is an unsupervised
machine learning technique. (T/F)
Given a transactional dataset containing d. Association Rule Mining/Market Basket Analysis
bakery products purchased by 1,000
customers, which of the following
methods is most appropriate to find 'how
many times a chocolate cupcake is
bought when a brownie and strawberry
muffin are bought together:
a.Decision Tree
b. Neural Network
c. K-means Clustering
d.Association Rule Mining/Market Basket
Analysis
2/
7
