Suppose a Bayesian spam filter is trained on a set of 100,000 spam emails and 4,000 emails that are not spam. The word "money" appears in 2,500 spam emails and 200 nonspam emails, the word "urgent" appears in 8,000 spam emails and 800 nonspam emails, the word "attention" appears in 20,000 spam emails and 80 nonspam emails, and the word "account" appears in 10,000 spam emails and 100 nonspam emails. Estimate the probability that a received email containing all four words of "money", "urgent", "attention", and "account" is spam. Will the email be rejected as spam if the threshold for rejecting spam is set at 80%?

Suppose a Bayesian spam filter is trained on a set of 100,000 spam emails and 4,000 emails that are not spam. The word "money" appears in 2,500 spam emails and 200 nonspam emails, the word "urgent" appears in 8,000 spam emails and 800 nonspam emails, the word "attention" appears in 20,000 spam emails and 80 nonspam emails, and the word "account" appears in 10,000 spam emails and 100 nonspam emails. Estimate the probability that a received email containing all four words of "money", "urgent", "attention", and "account" is spam. Will the email be rejected as spam if the threshold for rejecting spam is set at 80%?

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Similar questions

3. Give an example of a random variable X that takes on values from the set of all binary strings of length 4 where the min-entropy of X and the entropy of X are very different. Explain what is causing this phenomenon.
A histogram is plotted to get an idea of the probability distribution for a feature in a dataset. Given the histogram, what would you estimate for the probability that, for a random sample, the feature lies between 2 and 4? 0.175 0.150 0.125 0.100 0.075 0.050 0.025 0.000 0.5 0.125 0.05 0 0.25 -2 -6 8 10
Consider a world on which each individual belongs to a family of six, each family resides in its own home, each house has a specific address and every person in a certain house is given a unique name.Assume that this world has a postal service providing letters from source to destination. The postal service needs (1) the letter to be in an envelope and (2)that the address (and nothing else) of the destination house be clearly shown on the envelope. Suppose each family has a delegated member who receives letters for the other family members and distributes them. The letters do not actually give the receivers of the letters a hint. a. Would the postal service.ever have to open the envelope and inspect the letter and include the service under your protocol?
If the sequence number space is large enough to include k bits of information, you should carefully consider employing both the selective-repeat technique and the Go-Back-N strategy while searching for a solution. What is the biggest size that the sender window that we are allowed to use may be in total?
In the small world experiment, it was observed that anyone in the world could reach any other person in the world in about 5.2 intermediates (thus 6-degree of separation). This observation was made more than 50 years ago. The Internet should have shortened this average path distance. Suppose with the use of Internet and online social networks, every person in the world increases their number of friends by doubling it (2x). Please estimate the new degree of separation. Explain your estimation.
Consider a set of natural language sentences collected from Web pages. A human can like another human. A human can have a sex property of a man or a woman. A man can be the father of another human. A woman can be the mother of another human. A human can be married to another human. A human can have a BirthYear property of type “xs:Year”. If a human is married to another, then they like each other. viii. If a human is a mother or father, the human is a parent. Write a RDF schema and give a graphical presentation to describe these relationships.
Consider a world on which each individual belongs to a family of six, each family resides in its own home, each house has a specific address and every person in a certain house is given a unique name. Assume that this world has a postal service providing letters from source to destination. The postal service needs (1) the letter to be in an envelope and (2) that the address (and nothing else) of the destination house be clearly shown on the envelope. Suppose each family has a delegated member who receives letters for the other family members and distributes them. The letters do not actually give the receivers of the letters a hint. a. Define a procedure used by delegates to deliver letters from the transmitting family member to a receiving family member using the approach R1 above.
Using Matlab, plot the following ultrasound pressure wave as a function of x for t =1 P(t, x) = Poe** cos(@t – kx) where a = 0.15 neper/m, where neper is a dimensionless quantity, k = 1 rad/cm, o = 1 rad/s, and Po = 15 N/m2. Submit your ".m" file as well as the resulting graph labeled appropriately.
A unigram is a sequence of words of length one (i.e. a single word).• A bigram is a sequence of words of length two.• The conditional probability of an event E2 given another event E1, written p(E2|E1), is the probability that E2 will occur given that event E1 has already occurred.We write p(w(k)|w(k-1)) for the conditional probability of a word w in position k, w(k), given the immediately preceding word, w(k-1). You determine the conditional probabilities by determining unigram counts (the number of times each word appears, written c(w(k)), bigram counts (the number of times each pair of words appears, written c(w(k-1) w(k)), and then dividing each bigram count by the unigram count of the first word in the bigram:p(WORD(k)|WORD(k-1)) = c(WORD(k-1) WORD(k)) / c(WORD(k-1)) Apply and incorporate instrutions to code below. #include <stdio.h>//including headers#include <string.h>#include <stdlib.h> struct node{//structure intialization int data; struct node *next; };…
Let us say that we have a set of emails (without any labels) and your task is to determine which emails can be potentially a spam. The suitable method to solve such a problem is ? Decision tree Logistic regression K-means Linear regression
A publisher plans to boost the sales of its most popular magazine by sending out promotional mails. We refer to a customer as a responder if he/she subscribes to the magazine for the next year after receiving a promotional mail. Otherwise the customer is referred to as a non-responder. Denote responder by C1 and non-responder by C2. The publisher has built a model to classify each customer as either a responder or a non-responder. In practice only 1% of the customers are responders, and the remaining 99% are non-responders. In order to build an unbiased model, the publisher employed the oversampling method in creating the training set and the validation set, such that both datasets contain 50% responders and 50% non-responders. The validation confusion matrix is given below. Actual Class C1 C2 Predicted Class C1 645 112 C2 255 788 Round your answers to 3 digits after the decimal point. The oversampling factor of C1 is . The oversampling factor of…
Suppose that we test a discount system in some e-shop. The system can send a loyalty card to a client and admit a discount of 0% (no discount), 5%, or 10% according to the following rules: “No discount” is the default discount option. A nonregistered user has 0% discount by definition. If a registered user spent more than $1000 in the previous shopping sessions, and there were 19 or less shopping sessions, admit 5% discount. If a registered user spent more than $1000 in the previous shopping sessions and there were at least 20 shopping sessions, admit 10% discount. A loyalty card is sent only to registered customers who spent more than $1000 or had at least 20 shopping sessions. -Please write a java code for the given requirement