Effective methods for Email Classification: Is it a Business or Personal Email?

Milena Šošić1 and Jelena Graovac2

  1. Faculty of Mathematics, University of Belgrade
    Studentski Trg 16, 11000 Belgrade, Serbia
    pd202030@alas.matf.bg.ac.rs
  2. Faculty of Mathematics, University of Belgrade
    Studentski Trg 16, 11000 Belgrade, Serbia
    jgraovac@matf.bg.ac.rs

Abstract

With the steady increase in the number of Internet users, email remains the most popular and extensively used communication means. Therefore, email management is an important and growing problem for individuals and organiza-tions. In this paper, we deal with the classification of emails into two main cate-gories, Business and Personal. To find the best performing solution for this problem, a comprehensive set of experiments has been conducted with the deep learning al-gorithms: Bidirectional Long-Short Term Memory (BiLSTM) and Attention-based BiLSTM (BiLSTM+Att), together with traditional Machine Learning (ML) algo-rithms: Stochastic Gradient Descent (SGD) optimization applied on Support Vector Machine (SVM) and Extremely Randomized Trees (ERT) ensemble method. The variations of individual email and conversational email thread arc representations have been explored to reach the best classification generalization on the selected task. A special contribution of this paper is the extraction of a large number of ad-ditional lexical, conversational, expressional, emotional, and moral features, which proved very useful for differentiation between personal and official written con-versations. The experiments were performed on the publicly available Enron email benchmark corpora on which we obtained the State-Of-the-Art (SOA) results. As part of the submission, we have made our work publicly available to the scientific community for research purposes.

Key words

Email classification, business, personal, deep learning, BiLSTM, SGD, BERT embeddings, Tf-Idf, lexicons, NLP

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS220212034S

Publication information

Volume 19, Issue 3 (September 2022)
Year of Publication: 2022
ISSN: 1820-0214 (Print) 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Šošić, M., Graovac, J.: Effective methods for Email Classification: Is it a Business or Personal Email?. Computer Science and Information Systems, Vol. 19, No. 3, 1155-1175. (2022), https://doi.org/10.2298/CSIS220212034S