A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection

Hongmei He, Tim Watson, Carsten Maple, Jörn Mehnen, Ashutosh Tiwari

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

3 Citations (Scopus)

Abstract

The massive increase of spam is posing a very serious threat to email and SMS, which have become an important means of communication. Not only do spams annoy users, but they also become a security threat. Machine learning techniques have been widely used for spam detection. In this paper, we propose another form of deep learning, a linguistic attribute hierarchy, embedded with linguistic decision trees, for spam detection, and examine the effect of semantic attributes on the spam detection, represented by the linguistic attribute hierarchy. A case study on the SMS message database from the UCI machine learning repository has shown that a linguistic attribute hierarchy embedded with linguistic decision trees provides a transparent approach to in-depth analysing attribute impact on spam detection. This approach can not only efficiently tackle ‘curse of dimensionality’ in spam detection with massive attributes, but also improve the performance of spam detection when the semantic attributes are constructed to a proper hierarchy.
LanguageEnglish
Title of host publication2017 International Joint Conference on Neural Networks (IJCNN)
Place of PublicationPiscataway, NJ
PublisherIEEE
Number of pages8
ISBN (Electronic)9781509061822
DOIs
Publication statusPublished - 3 Jul 2017

Fingerprint

Linguistics
Semantics
Decision trees
Learning systems
Electronic mail
Deep learning
Communication

Keywords

  • deep learning
  • spam detection

Cite this

He, H., Watson, T., Maple, C., Mehnen, J., & Tiwari, A. (2017). A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection. In 2017 International Joint Conference on Neural Networks (IJCNN) Piscataway, NJ: IEEE. https://doi.org/10.1109/IJCNN.2017.7966343
He, Hongmei ; Watson, Tim ; Maple, Carsten ; Mehnen, Jörn ; Tiwari, Ashutosh. / A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection. 2017 International Joint Conference on Neural Networks (IJCNN). Piscataway, NJ : IEEE, 2017.
@inproceedings{decee7d6f1a3417d86624d01edce31a3,
title = "A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection",
abstract = "The massive increase of spam is posing a very serious threat to email and SMS, which have become an important means of communication. Not only do spams annoy users, but they also become a security threat. Machine learning techniques have been widely used for spam detection. In this paper, we propose another form of deep learning, a linguistic attribute hierarchy, embedded with linguistic decision trees, for spam detection, and examine the effect of semantic attributes on the spam detection, represented by the linguistic attribute hierarchy. A case study on the SMS message database from the UCI machine learning repository has shown that a linguistic attribute hierarchy embedded with linguistic decision trees provides a transparent approach to in-depth analysing attribute impact on spam detection. This approach can not only efficiently tackle ‘curse of dimensionality’ in spam detection with massive attributes, but also improve the performance of spam detection when the semantic attributes are constructed to a proper hierarchy.",
keywords = "deep learning, spam detection",
author = "Hongmei He and Tim Watson and Carsten Maple and J{\"o}rn Mehnen and Ashutosh Tiwari",
year = "2017",
month = "7",
day = "3",
doi = "10.1109/IJCNN.2017.7966343",
language = "English",
booktitle = "2017 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE",

}

He, H, Watson, T, Maple, C, Mehnen, J & Tiwari, A 2017, A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection. in 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, Piscataway, NJ. https://doi.org/10.1109/IJCNN.2017.7966343

A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection. / He, Hongmei; Watson, Tim; Maple, Carsten; Mehnen, Jörn; Tiwari, Ashutosh.

2017 International Joint Conference on Neural Networks (IJCNN). Piscataway, NJ : IEEE, 2017.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection

AU - He, Hongmei

AU - Watson, Tim

AU - Maple, Carsten

AU - Mehnen, Jörn

AU - Tiwari, Ashutosh

PY - 2017/7/3

Y1 - 2017/7/3

N2 - The massive increase of spam is posing a very serious threat to email and SMS, which have become an important means of communication. Not only do spams annoy users, but they also become a security threat. Machine learning techniques have been widely used for spam detection. In this paper, we propose another form of deep learning, a linguistic attribute hierarchy, embedded with linguistic decision trees, for spam detection, and examine the effect of semantic attributes on the spam detection, represented by the linguistic attribute hierarchy. A case study on the SMS message database from the UCI machine learning repository has shown that a linguistic attribute hierarchy embedded with linguistic decision trees provides a transparent approach to in-depth analysing attribute impact on spam detection. This approach can not only efficiently tackle ‘curse of dimensionality’ in spam detection with massive attributes, but also improve the performance of spam detection when the semantic attributes are constructed to a proper hierarchy.

AB - The massive increase of spam is posing a very serious threat to email and SMS, which have become an important means of communication. Not only do spams annoy users, but they also become a security threat. Machine learning techniques have been widely used for spam detection. In this paper, we propose another form of deep learning, a linguistic attribute hierarchy, embedded with linguistic decision trees, for spam detection, and examine the effect of semantic attributes on the spam detection, represented by the linguistic attribute hierarchy. A case study on the SMS message database from the UCI machine learning repository has shown that a linguistic attribute hierarchy embedded with linguistic decision trees provides a transparent approach to in-depth analysing attribute impact on spam detection. This approach can not only efficiently tackle ‘curse of dimensionality’ in spam detection with massive attributes, but also improve the performance of spam detection when the semantic attributes are constructed to a proper hierarchy.

KW - deep learning

KW - spam detection

U2 - 10.1109/IJCNN.2017.7966343

DO - 10.1109/IJCNN.2017.7966343

M3 - Conference contribution book

BT - 2017 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

CY - Piscataway, NJ

ER -

He H, Watson T, Maple C, Mehnen J, Tiwari A. A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection. In 2017 International Joint Conference on Neural Networks (IJCNN). Piscataway, NJ: IEEE. 2017 https://doi.org/10.1109/IJCNN.2017.7966343