Design of Computer Complex Spam Filtering System Based on Machine Learning Algorithm
Yong Jian Yang · 2023
SMS and E-mail have become common text communication methods in daily life because of their low rate, high speed and convenient sending and receiving. Sending spam not only consumes a lot of network resources and storage space, but also wastes users' precious time and disrupts the life and work of network users. The common contents of spam include advertising information, pornographic information, fake winning information, fraudulent information, pranks and so on. This paper studies the computer complex spam filtering system based on machine learning (ML) algorithm, analyzes the key technologies of the system and the problems existing in the original system, and puts forward the method of log feedback to analyze the filtered spam, extract keywords and update the filtered keyword database, so as to improve the system. When a new email arrives, we can extract feature words from it, and judge whether it is spam or not by calculating the obvious degree of spam features of feature words. Experiments and analysis show that the algorithm in this paper can effectively identify users who send spam, and at the same time, it can effectively control the rate of misidentifying normal users as spam users.