Why advanced sentiment handles nuance in NLP - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained sentiment analysis model.

NLP

from transformers import pipeline
sentiment_analyzer = pipeline([1])

Drag options to blanks, or click blank then click option'

A'text-classification'

B'translation_en_to_fr'

C'ner'

D'sentiment-analysis'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'text-classification' which is more general and may not handle nuance well.

Choosing unrelated pipelines like 'ner' or translation.

The 'sentiment-analysis' pipeline loads a model specialized for sentiment tasks.

2fill in blank

medium

Complete the code to analyze sentiment of the sentence.

NLP

result = sentiment_analyzer([1])[0]
print(result)

Drag options to blanks, or click blank then click option'

A['I love this movie!']

B'I love this movie!'

CI love this movie!

D('I love this movie!')

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a plain string instead of a list causes errors.

Using parentheses creates a tuple, which is not accepted.

The pipeline expects a list of strings as input to analyze sentiment.

3fill in blank

hard

Fix the error in the code to get the sentiment label.

NLP

label = result[1]['label']
print(label)

Drag options to blanks, or click blank then click option'

A.

B{

C[

D(

Attempts:

3 left

💡 Hint

Common Mistakes

Using dot notation causes AttributeError.

Using parentheses or curly braces causes syntax errors.

Use square brackets to access dictionary keys in Python.

4fill in blank

hard

Fill both blanks to create a function that returns sentiment label and score.

NLP

def analyze_sentiment(text):
    result = sentiment_analyzer([text])[[1]]
    return result[2]

Drag options to blanks, or click blank then click option'

A0

B'label'

C['label']

D'score'

Attempts:

3 left

💡 Hint

Common Mistakes

Using string '0' instead of integer 0 for indexing.

Using dot notation instead of square brackets for dictionary keys.

Index 0 gets the first result; ['label'] accesses the sentiment label.

5fill in blank

hard

Fill all three blanks to create a function that returns both label and score from sentiment analysis.

NLP

def analyze_sentiment_details(text):
    result = sentiment_analyzer([text])[[1]]
    label = result[2]
    score = result[3]
    return label, score

Drag options to blanks, or click blank then click option'

A0

B['label']

C['score']

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1 instead of 0 for indexing causes IndexError.

Using dot notation instead of square brackets for dictionary keys.

Index 0 gets the first result; ['label'] and ['score'] access the respective values.