Implementation of Naïve Bayes and Gini Index for Spam Email Classification
Email is a medium of information that is still frequently used by people today. At the moment email still has an endless problem that is spam email. Spam email is an email that can pollute, damage or disturb the recipient. In this study, we show the performance and accuracy of Multinomial Naïve Bayes (MNNB) and Complete Gini-Index Text (GIT) for use in spam email filtering. In this study, we used 6 cross-validations as testers for the built classification machines. We found that the average yield can exceed Multinomial Naïve Bayes without using feature selection which only uses 80000 features with a difference of 0.39%. Feature selection also increases speed during classification and can reduce features that are less relevant to the category to be classified.
Code (1)
Tasks
feature selectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Classification of Spam Emails through Hierarchical Clustering and Supervised Learning
Spammers take advantage of email popularity to send indiscriminately unsolicited emails. Although researchers and organizations continuously develop anti-spam filters based on binary classification, spammers bypass them …
Binary ClassificationClassificationClusteringGeneral ClassificationBuilding an Effective Email Spam Classification Model with spaCy
Today, people use email services such as Gmail, Outlook, AOL Mail, etc. to communicate with each other as quickly as possible to send information and official letters. Spam or junk mail is a major challenge to this type …
ClassificationSpam detectionSpam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection
This paper investigates the effectiveness of large language models (LLMs) in email spam detection by comparing prominent models from three distinct families: BERT-like, Sentence Transformers, and Seq2Seq. Additionally, w…
BenchmarkingSentenceSpam detectionClassifying spam emails using agglomerative hierarchical clustering and a topic-based approach
Spam emails are unsolicited, annoying and sometimes harmful messages which may contain malware, phishing or hoaxes. Unlike most studies that address the design of efficient anti-spam filters, we approach the spam email p…
ClusteringA Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters
Naive Bayes spam filters are highly susceptible to data poisoning attacks. Here, known spam sources/blacklisted IPs exploit the fact that their received emails will be treated as (ground truth) labeled spam examples, and…
Data Poisoning