Please see attached file.
1. We want to build a naive Bayes sentiment classifier using add-1 smoothing. Here is our training
set:
– the movie has no plot
– honestly pretty boring
+ pretty interesting movie
Test Set:
pretty enjoyable plot
Answer the questions below given the sets above:
1. Compute the prior for the two classes + and -, and the likelihoods for each word given the
class (leave in the form of fractions).
2. Would using binary multinomial Naive Bayes change anything?
3. Why do you add |V| to the denominator of add-1 smoothing, instead of just counting the
words in one class?
2. Go to the Sentiment demo. Come up with 1 sentence that the classifier gets wrong. Explain, the
best you can, what is causing the error?
https://demo.allennlp.org/sentiment-analysis/glove-sentiment-analysis
