Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification

Zheming Zuo, Jie Li, Philip Anderson, Longzhi Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearch

13 Downloads (Pure)

Abstract

Online child grooming detection has recently attracted intensive research interests from both the machine learning community and digital forensics community due to its great social impact. The existing data-driven approaches usually face the challenges of lack of training data and the uncertainty of classes in terms of the classification or decision boundary. This paper proposes a grooming detection approach in an effort to address such uncertainty based on a data set derived from a publicly available profiling data set. In particular, the approach firstly applies the conventional text feature extraction approach in identifying the most significant words in the data set. This is followed by the application of a fuzzy-rough feature selection approach in reducing the high dimensions of the selected words for fast processing, which at the same time addressing the uncertainty of class boundaries. The experimental results demonstrate the efficiency and efficacy of the proposed approach in detecting child grooming.
Original languageEnglish
Title of host publication2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
PublisherIEEE
Pages1-8
Number of pages8
ISBN (Electronic)978-1-5090-6020-7
DOIs
Publication statusPublished - 13 Jul 2018
Event2018 IEEE International Conference on Fuzzy Systems - Rio de Janeiro, Brazil
Duration: 8 Jul 201813 Jul 2018

Conference

Conference2018 IEEE International Conference on Fuzzy Systems
Abbreviated titleFUZZ- IEEE 2018
CountryBrazil
CityRio de Janeiro
Period8/07/1813/07/18

Fingerprint

Feature extraction
Learning systems
Processing
Uncertainty
Digital forensics

Cite this

Zuo, Z., Li, J., Anderson, P., & Yang, L. (2018). Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification. In 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) (pp. 1-8). IEEE. https://doi.org/10.1109/FUZZ-IEEE.2018.8491591
Zuo, Zheming ; Li, Jie ; Anderson, Philip ; Yang, Longzhi. / Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification. 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE, 2018. pp. 1-8
@inproceedings{1583e9855deb4e6a8ef069e0dcf4e3da,
title = "Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification",
abstract = "Online child grooming detection has recently attracted intensive research interests from both the machine learning community and digital forensics community due to its great social impact. The existing data-driven approaches usually face the challenges of lack of training data and the uncertainty of classes in terms of the classification or decision boundary. This paper proposes a grooming detection approach in an effort to address such uncertainty based on a data set derived from a publicly available profiling data set. In particular, the approach firstly applies the conventional text feature extraction approach in identifying the most significant words in the data set. This is followed by the application of a fuzzy-rough feature selection approach in reducing the high dimensions of the selected words for fast processing, which at the same time addressing the uncertainty of class boundaries. The experimental results demonstrate the efficiency and efficacy of the proposed approach in detecting child grooming.",
author = "Zheming Zuo and Jie Li and Philip Anderson and Longzhi Yang",
year = "2018",
month = "7",
day = "13",
doi = "10.1109/FUZZ-IEEE.2018.8491591",
language = "English",
pages = "1--8",
booktitle = "2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)",
publisher = "IEEE",

}

Zuo, Z, Li, J, Anderson, P & Yang, L 2018, Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification. in 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE, pp. 1-8, 2018 IEEE International Conference on Fuzzy Systems, Rio de Janeiro, Brazil, 8/07/18. https://doi.org/10.1109/FUZZ-IEEE.2018.8491591

Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification. / Zuo, Zheming; Li, Jie; Anderson, Philip; Yang, Longzhi.

2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE, 2018. p. 1-8.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearch

TY - GEN

T1 - Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification

AU - Zuo, Zheming

AU - Li, Jie

AU - Anderson, Philip

AU - Yang, Longzhi

PY - 2018/7/13

Y1 - 2018/7/13

N2 - Online child grooming detection has recently attracted intensive research interests from both the machine learning community and digital forensics community due to its great social impact. The existing data-driven approaches usually face the challenges of lack of training data and the uncertainty of classes in terms of the classification or decision boundary. This paper proposes a grooming detection approach in an effort to address such uncertainty based on a data set derived from a publicly available profiling data set. In particular, the approach firstly applies the conventional text feature extraction approach in identifying the most significant words in the data set. This is followed by the application of a fuzzy-rough feature selection approach in reducing the high dimensions of the selected words for fast processing, which at the same time addressing the uncertainty of class boundaries. The experimental results demonstrate the efficiency and efficacy of the proposed approach in detecting child grooming.

AB - Online child grooming detection has recently attracted intensive research interests from both the machine learning community and digital forensics community due to its great social impact. The existing data-driven approaches usually face the challenges of lack of training data and the uncertainty of classes in terms of the classification or decision boundary. This paper proposes a grooming detection approach in an effort to address such uncertainty based on a data set derived from a publicly available profiling data set. In particular, the approach firstly applies the conventional text feature extraction approach in identifying the most significant words in the data set. This is followed by the application of a fuzzy-rough feature selection approach in reducing the high dimensions of the selected words for fast processing, which at the same time addressing the uncertainty of class boundaries. The experimental results demonstrate the efficiency and efficacy of the proposed approach in detecting child grooming.

UR - https://ieeexplore.ieee.org/document/8491591

U2 - 10.1109/FUZZ-IEEE.2018.8491591

DO - 10.1109/FUZZ-IEEE.2018.8491591

M3 - Conference contribution

SP - 1

EP - 8

BT - 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

PB - IEEE

ER -

Zuo Z, Li J, Anderson P, Yang L. Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification. In 2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE. 2018. p. 1-8 https://doi.org/10.1109/FUZZ-IEEE.2018.8491591