Spam detection problem: assume that there are several messages as below 1) Hi, here is a secret 2) Click secret link 3) Lunch together? 4) Secret offer 5) Play soccer today 6) Let us go for lunch 7) Top secret 8) Let us meet at my office 9) Discussing project today 10) It is soccer time! And 1), 2), 4) and 7) are identified as spam. Please answer the following questions: 3. To represent the problem, we will define a dictionary first. How many words will be in the dictionary? What's the estimate probability of the spam messages in the system P(spam)