languages & linguistics
intermediate
10 sample questions
Sentiment Analysis MCQ Practice Test
Using algorithms to identify and extract subjective information from text.
Q1. In sentiment analysis, which of the following techniques is used to handle out-of-vocabulary (OOV) words, which are words that have not been seen during training?
-
A. Part-of-speech tagging
-
B. Named entity recognition
-
C. Subword modeling ✓
-
D. Dependency parsing
Explanation: Subword modeling is a technique used in natural language processing to handle out-of-vocabulary words by breaking down words into subword units, such as wordpieces or character n-grams. This approach allows models to learn representations of words that are not seen during training, improving their ability to handle OOV words.
Q2. In sentiment analysis, what is the primary goal of using a technique called “aspect-based sentiment analysis”?
-
A. To identify the sentiment of a sentence as a whole, rather than its individual components
-
B. To analyze the sentiment of a specific aspect of a product or service, such as its price or quality ✓
-
C. To determine the overall sentiment of a text, regardless of its individual components or aspects
-
D. To classify text as positive, negative, or neutral based on its linguistic features
Explanation: Aspect-based sentiment analysis is a technique used in sentiment analysis to identify the sentiment of specific aspects of a product or service. For example, analyzing the sentiment of a customer review towards the price of a product, rather than the product as a whole.
Q3. Which of the following sentiment analysis techniques uses a combination of machine learning and rule-based approaches to classify text as positive, negative, or neutral?
-
A. SVM (Support Vector Machine) with n-gram features
-
B. Rule-based approach with lexicon-based sentiment scoring
-
C. Deep learning-based approach with convolutional neural networks
-
D. Hybrid approach combining machine learning and rule-based methods ✓
Explanation: A hybrid approach combines the strengths of machine learning and rule-based methods to perform sentiment analysis. Machine learning techniques, such as support vector machines, can learn complex patterns in text data, while rule-based methods can leverage domain-specific knowledge and linguistic rules to improve accuracy.
Q4. In sentiment analysis, which of the following techniques is *most directly* used to handle negation and intensification in text data?
-
A. Part-of-speech tagging
-
B. Named entity recognition
-
C. Dependency parsing
-
D. Semantic role labeling with negation handling ✓
Explanation: Semantic role labeling with negation handling is a technique specifically designed to identify and interpret negation and intensification by analyzing the relationships between words and phrases in a sentence. Dependency parsing can be used as a supporting technique, but is not the primary method for handling negation and intensification.
Q5. In sentiment analysis, which of the following techniques is used to handle negation and intensification in text, such as “not good” or “very bad”?
-
A. Part-of-speech tagging and named entity recognition
-
B. Dependency parsing and semantic role labeling
-
C. Rule-based approach using lexicons and dictionaries ✓
-
D. Machine learning-based approach using supervised learning
Explanation: A rule-based approach using lexicons and dictionaries is often employed to handle negation and intensification in sentiment analysis. This involves creating rules to identify and handle words that indicate negation or intensification, such as “not” or “very”, and using lexicons and dictionaries to provide context and meaning to these words.
Q6. In sentiment analysis, which of the following techniques is used to handle negation and intensification in phrases like "not bad" or "very good"?
-
A. Part-of-speech tagging
-
B. Named Entity Recognition
-
C. Dependency Parsing
-
D. Semantic Role Labeling with negation and intensification handling ✓
Explanation: Semantic Role Labeling (SRL) is a technique used in natural language processing to identify the roles played by entities in a sentence. Some SRL systems can handle negation and intensification by analyzing the semantic relationships between entities and their modifiers, allowing them to accurately capture the sentiment expressed in phrases like "not bad" or "very good".
Q7. A sentiment analysis model is trained on a dataset that contains a mix of positive, negative, and neutral reviews. However, the model is biased towards detecting negative sentiment due to the presence of a large number of negative reviews. Which of the following techniques can be used to mitigate this bias?
-
A. oversampling the minority class of positive reviews
-
B. undersampling the majority class of negative reviews
-
C. using a class weight approach to penalize the model for misclassifying positive reviews ✓
-
D. using a sentiment lexicon that is biased towards positive words
Explanation: A class weight approach can be used to penalize the model for misclassifying positive reviews, thus mitigating the bias towards negative sentiment. This is achieved by assigning a higher weight to the positive class, making it more difficult for the model to misclassify positive reviews as negative.
Q8. In sentiment analysis, which of the following techniques is used to handle negation and intensification of sentiment expressions?
-
A. Part-of-speech tagging and named entity recognition
-
B. Dependency parsing and semantic role labeling
-
C. Rule-based approach and machine learning ✓
-
D. Sentiment lexicon and aspect-based sentiment analysis
Explanation: A rule-based approach involves using hand-crafted rules to identify negation and intensification, while machine learning can be used to learn these patterns from labeled data. This combination is often used in sentiment analysis to handle complex sentiment expressions.
Q9. A sentiment analysis model is trained on a dataset of movie reviews. The model is designed to classify reviews as either positive or negative. However, the model is found to have a bias towards classifying reviews that contain words related to emotions such as “love” and “sad” as positive or negative respectively. This phenomenon is an example of:
-
A. Affective bias ✓
-
B. Contextual insensitivity
-
C. Semantic ambiguity
-
D. Pragmatic incoherence
Explanation: Affective bias refers to the tendency of a sentiment analysis model to be influenced by emotional words or phrases, leading to biased classification results. In this case, the model's bias towards emotional words such as “love” and “sad” is an example of affective bias.
Q10. A sentiment analysis model is trained on a dataset of movie reviews. The model uses a technique called “aspect-based” sentiment analysis, which identifies the sentiment of a review towards specific aspects of a movie, such as the plot, acting, or music. What is the primary advantage of using aspect-based sentiment analysis in this context?
-
A. It allows the model to capture nuanced sentiment towards specific aspects of a movie. ✓
-
B. It enables the model to identify the overall sentiment of a review without considering specific aspects.
-
C. It facilitates the comparison of sentiment across different aspects of a movie.
-
D. It simplifies the process of training a sentiment analysis model on a large dataset.
Explanation: Aspect-based sentiment analysis enables the model to identify and analyze sentiment towards specific aspects of a movie, providing a more detailed and nuanced understanding of the review's content.
That was just a sample. Sign up to unlock the full question bank with timed tests and certificates.
Sign Up Free