Spam detection using Catboost integration algorithm

TianLin Zhang; YouFeng Niu; Rong Ma; MengYuan Zhao; DuoYang Song; HengBin Liu

doi:10.1117/12.2672788

28 March 2023 Spam detection using Catboost integration algorithm

TianLin Zhang, YouFeng Niu, Rong Ma, MengYuan Zhao, DuoYang Song, HengBin Liu

Proceedings Volume 12597, Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022); 125973A (2023) https://doi.org/10.1117/12.2672788
Event: Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), 2022, Nanjing, China

Abstract

This paper introduces the background and significance of building a CatBoost-based spam detection model and proposes a new research approach on the classical research model. Besides, a large number of network resources are occupied which makes 85% of the system resources of the mail server are used for the identification of spam. It is not only a waste of resources, but may even lead to network congestion and paralysis, affecting the normal business email communication of enterprises. In this study, we use the Enron-Spam dataset, which is currently the most publicly available dataset used in email-related research. First, we use word bagging processing and TF-IDF processing for feature extraction, and then CatBoost integration algorithm is used for training. The final accuracy of the model is more than 98%. Compared with the conventional model, the model has better performance, which can effectively improve the accuracy of spam detection and identification.

Citation Download Citation

TianLin Zhang, YouFeng Niu, Rong Ma, MengYuan Zhao, DuoYang Song, and HengBin Liu "Spam detection using Catboost integration algorithm", Proc. SPIE 12597, Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), 125973A (28 March 2023); https://doi.org/10.1117/12.2672788

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available