Unit 4 - Practice Quiz

INT344 50 Questions
0 Correct 0 Wrong 50 Left
0/50

1 In the context of sentiment analysis using Logistic Regression, what is the primary purpose of feature extraction?

A. To convert numerical vectors back into text
B. To increase the length of the sentences
C. To translate text from one language to another
D. To transform raw text into numerical representations like vectors

2 Which function is used in Logistic Regression to map the output to a probability value between 0 and 1?

A. Tangent Function
B. Linear Function
C. Sigmoid Function
D. ReLU Function

3 When extracting features for sentiment analysis, what does a frequency dictionary typically map?

A. (Word, Sentiment Label) pairs to the count of occurrences
B. Word length to Sentence length
C. Each word to its synonym
D. Process ID to Memory usage

4 In a binary logistic regression classifier for sentiment analysis, if the sigmoid output h(x) >= 0.5, how is the sentiment classified?

A. Neutral
B. Negative
C. Positive
D. Undefined

5 What is the formula for the sigmoid function, σ(z)?

A. e^z / (1 + e^z)
B. log(z)
C. 1 / (1 - e^-z)
D. 1 / (1 + e^-z)

6 In the feature vector representation X = [1, sum_pos, sum_neg], what does the '1' usually represent?

A. The count of the first word
B. The learning rate
C. The bias unit (intercept term)
D. The classification threshold

7 Which preprocessing step is commonly performed before feature extraction to reduce the vocabulary size without losing semantic meaning?

A. Stemming and removing stop words
B. Duplicating sentences
C. Capitalizing all letters
D. Removing all vowels

8 What is the 'Cost Function' used in Logistic Regression generally called?

A. Mean Squared Error
B. Cross-Entropy Loss (Log Loss)
C. Hinge Loss
D. Absolute Error

9 What is the goal of Gradient Descent in training a Logistic Regression model?

A. To remove the bias term
B. To set all weights to zero
C. To minimize the cost function by iteratively updating weights
D. To maximize the cost function

10 In Bayes' Rule, what does P(A|B) represent?

A. The prior probability of A
B. The posterior probability of A given B
C. The joint probability of A and B
D. The probability of B given A

11 Why is the Naive Bayes classifier called 'Naive'?

A. It was developed by a naive mathematician
B. It assumes that features are independent of each other given the class
C. It cannot handle complex text
D. It requires very little training data

12 What is the formula for Bayes' Theorem?

A. P(A|B) = P(B|A) * P(A) / P(B)
B. P(A|B) = P(B|A) + P(A)
C. P(A|B) = P(A) * P(B)
D. P(A|B) = P(A) / P(B)

13 In Naive Bayes Sentiment Analysis, what is 'Laplacian Smoothing' used for?

A. To handle words with zero probability (words not seen in training)
B. To smooth the decision boundary
C. To remove stop words
D. To average the sentiment scores

14 If a word appears in the positive corpus but not the negative corpus, what happens to its probability P(W|Negative) without smoothing?

A. It becomes 0.5
B. It becomes 1
C. It becomes infinity
D. It becomes 0

15 In Logistic Regression, if the dot product θ^T * x is 0, what is the output of the sigmoid function?

A. undefined
B. 0
C. 0.5
D. 1

16 Which of the following describes the 'Prior Probability' P(Positive) in Naive Bayes?

A. Probability of a document being positive based on the training set distribution
B. Probability of a document being positive given a specific word
C. Total number of words in the dictionary
D. Probability of a word being positive

17 Why do we typically use Log Likelihood in Naive Bayes calculations instead of raw probabilities?

A. To prevent numerical underflow from multiplying many small probabilities
B. Because logarithms are faster to compute than addition
C. To convert negative numbers to positive
D. To make the calculation harder

18 In the Naive Bayes inference formula, if the sum of the Log Prior and Log Likelihoods is greater than 0, the sentiment is classified as:

A. Neutral
B. Negative
C. Ambiguous
D. Positive

19 What is a 'sparse representation' in the context of NLP feature vectors?

A. A vector where most elements are zero
B. A vector with a small dimension
C. A vector containing only negative numbers
D. A vector with mostly non-zero values

20 Which component of the Naive Bayes classifier represents the 'Evidence' in Bayes' rule?

A. P(Data)
B. P(Class | Data)
C. P(Class)
D. P(Data | Class)

21 In Logistic Regression, what is the dimension of the weight vector θ if the feature vector x has dimension V+1?

A. 1
B. V+1
C. V
D. V*2

22 Which algorithm is considered a 'Generative' model?

A. Naive Bayes
B. Perceptron
C. Logistic Regression
D. Support Vector Machine

23 Which algorithm is considered a 'Discriminative' model?

A. Gaussian Mixture Model
B. Naive Bayes
C. Hidden Markov Model
D. Logistic Regression

24 What is the 'Lambda' (λ) term in the context of Naive Bayes ratio calculation?

A. The bias unit
B. The learning rate
C. The number of classes
D. The smoothing parameter

25 When extracting features for Logistic Regression, if the word 'happy' appears 3 times in a tweet, and 'happy' has a positive frequency of 100 and negative frequency of 5 in the corpus, how is this typically utilized?

A. The word is ignored
B. The number 3 is the only feature used
C. The ratio 100/5 is used as the weight
D. The counts 100 and 5 contribute to the aggregate sums in the feature vector

26 What is the main advantage of Logistic Regression over Naive Bayes?

A. It handles missing data better
B. It is always faster to train
C. It is a generative model
D. It does not require independent features

27 In the context of Naive Bayes, what is V?

A. The vector dimension
B. The number of classes
C. The validation set size
D. The vocabulary size (number of unique words)

28 If the learning rate in Logistic Regression is too large, what might happen?

A. The model will always find the global minimum
B. The cost function becomes 0 immediately
C. The model converges very slowly
D. The model may overshoot the minimum and fail to converge

29 Which of the following is a hyperparameter in Logistic Regression?

A. The weight vector θ
B. The bias term
C. The feature vector x
D. The learning rate α

30 How is the 'Log Prior' calculated for the positive class?

A. log(N_pos / N_neg)
B. log(N_pos / N_total)
C. log(N_neg / N_pos)
D. log(V)

31 What is the range of values for the output of the standard Naive Bayes probability calculation P(y|x) before applying logs?

A. (-infinity, +infinity)
B. [0, 100]
C. [0, 1]
D. [-1, 1]

32 Which sentiment lexicon is purely generated from the training data in the approaches discussed?

A. The Lambda dictionary (Log Likelihood ratios of words)
B. SentiWordNet
C. Google Dictionary
D. WordNet

33 When predicting with Naive Bayes, if a word in the test sentence is not in the training vocabulary (V), what is the standard action?

A. Assign it a random probability
B. Re-train the model
C. Halt the program
D. Discard it (ignore it)

34 What is 'Sentiment Analysis' primarily classifying?

A. The language of the text
B. The topic of the text
C. The emotional tone or opinion (e.g., Positive/Negative)
D. The grammatical structure

35 In Logistic Regression, the decision boundary is:

A. Non-linear
B. Polynomial
C. Circular
D. Linear

36 The denominator for calculating P(w|class) with Laplacian smoothing is:

A. Count(w in class) + 1
B. V
C. N_class (total words in class) + V (vocabulary size)
D. N_class

37 What does a negative value in a word's Log Likelihood (Lambda) score imply in Sentiment Analysis?

A. The word is neutral
B. The word is indicative of Positive sentiment
C. The word is a stop word
D. The word is indicative of Negative sentiment

38 Which of the following is a stop word?

A. Love
B. Amazing
C. The
D. Terrible

39 In a confusion matrix for binary classification, what is a False Positive?

A. Correctly predicting positive
B. Incorrectly predicting positive when the actual class is negative
C. Correctly predicting negative
D. Incorrectly predicting negative when the actual class is positive

40 What is the primary reason for lowercasing text during preprocessing?

A. To remove punctuation
B. To ensure 'Good' and 'good' are treated as the same feature
C. It looks better
D. To detect sentence boundaries

41 If a Logistic Regression model is overfitted, how will it perform?

A. Poorly on training data, poorly on test data
B. Well on training data, poorly on test data
C. Well on training data, well on test data
D. Poorly on training data, well on test data

42 Which formula represents the update rule for weight θ_j in Gradient Descent?

A. θ_j := θ_j / α
B. θ_j := θ_j + α * dJ/dθ_j
C. θ_j := θ_j - α * dJ/dθ_j
D. θ_j := dJ/dθ_j

43 In Naive Bayes, what assumption allows us to multiply probabilities of individual words?

A. Normal Distribution
B. Linear Separability
C. Conditional Independence
D. Homoscedasticity

44 What is Tokenization?

A. Splitting a string of text into individual words or terms
B. Removing special characters
C. Converting words to numbers
D. Translating text

45 Which value of probability corresponds to the logit (log-odds) value of 0?

A. 1
B. 0
C. 0.5
D. Infinity

46 What is the interpretation of weights in Logistic Regression for Sentiment Analysis?

A. They represent the index of the word
B. They are random numbers
C. They represent the importance and direction (positive/negative) of a feature
D. They represent the frequency of words

47 For a balanced dataset, which metric is most straightforward to evaluate performance?

A. Mean Squared Error
B. Precision only
C. Accuracy
D. Recall only

48 In vector space models, what is 'Oov'?

A. Out of vector
B. Out of vocabulary
C. Over optimization value
D. Object oriented vector

49 The conditional probability P(Word|Positive) is conceptually similar to:

A. The probability that the sentiment is Positive given the word
B. How likely the word is to appear if the sentiment is known to be Positive
C. The probability of the word being a stop word
D. How often the word appears in the whole dataset

50 Which technique is essentially a 'probabilistic classifier' based on applying Bayes' theorem?

A. K-Means
B. K-Nearest Neighbors
C. Naive Bayes
D. Decision Trees