Predictive Analytics with TensorFlow 8.4: CNN-based Predictive Model for Sentiment Analysis

What is the main advantage of using CNN for sentiment analysis over traditional methods?

• CNNs are faster to train.

• CNNs can handle image data.

• CNNs can capture patterns in text data.

• CNNs require less data preprocessing.

Why is an embedding layer necessary in a CNN model for text data?

• To reduce the model's complexity.

• To convert text data into a format suitable for convolution.

• To handle missing data.

• To increase the model's speed.

What is the purpose of the clean STR function in data preprocessing?

• To clean and standardize text data.

• To generate labels for the data.

• To convert text data into numeric vectors.

• To split data into training and test sets.

Which method is used to shuffle data during batch generation?

• Epoch Shuffler

• Data Loader

• Batch ITR

• Shuffle Data

What is the role of the Adam Optimizer in training the CNN model?

• To evaluate the model's accuracy.

• To split the data into batches.

• To optimize the cost function.

• To initialize the model weights.

Which performance metric is NOT mentioned for evaluating the CNN model?

• Accuracy

• Precision

• Recall

• Mean Squared Error

What is the final accuracy achieved by the CNN model for sentiment analysis?

• 90%

• 85%

• 97%

• 99%