Natural Language Processing Sentiment Analysis and Text Classification 2

Question 1

What is a lexicon-based approach to sentiment analysis?

Accepted Answer

Using a pre-built dictionary of words labeled with their sentiment polarity scores to calculate overall text sentiment

Answer

Training a neural network on labeled sentiment data

Answer

Using clustering to group texts by emotional tone

Answer

Applying dependency parsing to identify opinion expressions

Question 2

What is multi-label text classification?

Accepted Answer

Assigning multiple non-mutually exclusive labels to a single text, such as tagging a news article with several topics simultaneously

Answer

Classifying text into a large number of fine-grained categories

Answer

Applying a different classifier for each sentence in a document

Answer

Using an ensemble of binary classifiers for each class

Question 3

What is opinion mining?

Accepted Answer

Extracting subjective information such as opinions, evaluations, and emotions from text at scale

Answer

Mining text corpora for factual information about a topic

Answer

Detecting plagiarism in documents

Answer

Removing opinionated words from text before analysis

Question 4

How does class imbalance affect sentiment classification model training?

Accepted Answer

A model trained on imbalanced data tends to be biased toward the majority class and performs poorly on minority classes

Answer

Class imbalance improves recall for the minority class

Answer

It makes the model faster to train

Answer

It has no effect if enough data is available overall

Question 5

What is the SQuAD dataset commonly used for in NLP?

Accepted Answer

Benchmarking extractive reading comprehension and question answering models

Answer

Evaluating sentiment classification accuracy

Answer

Training named entity recognition systems

Answer

Measuring machine translation quality

Question 6

What does the macro-averaged F1 score measure in multi-class classification?

Accepted Answer

The unweighted mean of per-class F1 scores, treating all classes equally regardless of their frequency

Answer

The F1 score weighted by the number of samples in each class

Answer

The F1 score computed only on the majority class

Answer

The harmonic mean of precision and recall across the full dataset