NLP Sentiment Analysis 3

Question 1

What is 'subjectivity detection' as a preprocessing step in sentiment analysis?

Accepted Answer

Distinguishing objective factual statements from subjective opinionated text

Answer

Subjectivity detection filters out objective sentences so sentiment analysis focuses only on opinion-bearing content.

Question 2

Which technique helps capture long-range dependencies in sentiment classification using deep learning?

Accepted Answer

LSTM or Transformer-based model

Answer

LSTMs and Transformers maintain context across long sequences, capturing dependencies that bag-of-words models miss.

Question 3

What does 'opinion mining' typically extract beyond overall sentiment polarity?

Accepted Answer

Opinion holders, opinion targets, and sentiment expressions

Answer

Opinion mining identifies who holds the opinion, what the opinion is about, and the expressed sentiment toward it.

Question 4

How does 'contextualized word embedding' (e.g., BERT) improve sentiment analysis over static embeddings?

Accepted Answer

It generates different vector representations for the same word depending on its context

Answer

Contextualized embeddings like BERT encode surrounding context, so 'great' in a positive vs. sarcastic sentence gets different representations.

Question 5

Which strategy is commonly used to handle sarcasm detection in sentiment analysis?

Accepted Answer

Incorporating incongruity signals between sentiment and context or using multimodal cues

Answer

Sarcasm often involves contrast between literal positive words and negative context, so detecting incongruity is a key strategy.

NLP Practice Test