Sentiment with context (sarcasm, negation) in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the text data for sentiment analysis.

NLP

texts = ["I love this movie!", "This is not good.", "Absolutely fantastic!"]
labels = [1, 0, 1]

from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer()
X = vectorizer.[1](texts)

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

Atransform

Bfit_transform

Cfit

Dtoarray

Attempts:

3 left

💡 Hint

Common Mistakes

Using transform before fitting the vectorizer.

Using fit without transforming the texts.

We use fit_transform to learn the vocabulary and transform the texts into feature vectors in one step.

2fill in blank

medium

Complete the code to train a logistic regression model for sentiment classification.

NLP

from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.[1](X, labels)

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

Afit

Bscore

Cpredict

Dtransform

Attempts:

3 left

💡 Hint

Common Mistakes

Using predict before training the model.

Using transform which is not a model method.

We use fit to train the model on the feature vectors and labels.

3fill in blank

hard

Fix the error in the code to correctly predict sentiment for new texts.

NLP

new_texts = ["I don't like this.", "What a great day!"]
X_new = vectorizer.[1](new_texts)
predictions = model.predict(X_new)

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

Afit_transform

Bpredict

Ctransform

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using fit_transform on new data which changes the vocabulary.

Using fit which does not return transformed data.

For new data, we only transform using the existing vocabulary, not fit again.

4fill in blank

hard

Fill both blanks to create a function that detects negation words and adjusts sentiment accordingly.

NLP

def adjust_for_negation(text, sentiment):
    negations = ['not', 'no', 'never', 'none']
    words = text.lower().split()
    if any(word [1] negations for word in words):
        return 1 [2] sentiment
    return sentiment

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

Ain

Bnot in

C-

D+

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'not in' which checks the opposite condition.

Adding 1 instead of subtracting to flip sentiment.

We check if any word is in negations and then flip the sentiment by subtracting it from 1.

5fill in blank

hard

Fill all three blanks to build a simple sarcasm detector that flags sarcastic sentences containing 'yeah right' or 'as if'.

NLP

def detect_sarcasm(text):
    sarcasm_phrases = [[1], [2]]
    text_lower = text.lower()
    for phrase in sarcasm_phrases:
        if phrase [3] text_lower:
            return True
    return False

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

A"yeah right"

B"as if"

Cin

Dnot in

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'not in' which checks the opposite condition.

Not quoting the sarcasm phrases as strings.

We list sarcasm phrases as strings and check if each phrase is in the lowercased text.