Email is one of the most widely used ways to communicate, with millions of
people and businesses relying on it to communicate and share knowledge and
information on a daily basis. Nevertheless, the rise in email users has
occurred a dramatic increase in spam emails in recent years. Processing and
managing emails properly for individuals and companies are getting increasingly
difficult. This article proposes a novel technique for email spam detection
that is based on a combination of convolutional neural networks, gated
recurrent units, and attention mechanisms. During system training, the network
is selectively focused on necessary parts of the email text. The usage of
convolution layers to extract more meaningful, abstract, and generalizable
features by hierarchical representation is the major contribution of this
study. Additionally, this contribution incorporates cross-dataset evaluation,
which enables the generation of more independent performance results from the
model's training dataset. According to cross-dataset evaluation results, the
proposed technique advances the results of the present attention-based
techniques by utilizing temporal convolutions, which give us more flexible
receptive field sizes are utilized. The suggested technique's findings are
compared to those of state-of-the-art models and show that our approach
outperforms them.

本文提出了一种新的基于一种结合了卷积神经网络、带门循环单元和注意机制的技术的邮件垃圾邮件检测方法，该方法利用卷积层逐层提取意义深刻、抽象且具有泛化性的特征，同时包含跨数据集评估。经过交叉数据集评估，本方法优于现有基于注意机制的技术，实现了更灵活的接受域大小的使用。

使用分层注意力混合深度学习方法进行电子邮件垃圾邮件检测

Email Spam Detection Using Hierarchical Attention Hybrid Deep Learning Method

Email messages have been an important mode of communication, not only for
work, but also for social interactions and marketing. When messages have time
sensitive information, it becomes relevant for the sender to know what is the
expected time within which the email will be read by the recipient. In this
paper we use a survival analysis framework to predict the time to open an email
once it has been received. We use the Cox Proportional Hazards (CoxPH) model
that offers a way to combine various features that might affect the event of
opening an email. As an extension, we also apply a mixture model (MM) approach
to CoxPH that distinguishes between recipients, based on a latent state of how
prone to opening the messages each individual is. We compare our approach with
standard classification and regression models. While the classification model
provides predictions on the likelihood of an email being opened, the regression
model provides prediction of the real-valued time to open. The use of survival
analysis based methods allows us to jointly model both the open event as well
as the time-to-open. We experimented on a large real-world dataset of marketing
emails sent in a 3-month time duration. The mixture model achieves the best
accuracy on our data where a high proportion of email messages go unopened.

本文介绍如何利用生存分析框架来预测电子邮件收件人打开邮件所需的时间，通过 Cox 比例风险模型和混合模型进行模型训练，并和传统分类和回归模型进行对比，在实际的市场营销数据中取得了最佳的精度表现。