Automatic detection of cyberbullying using multi-feature based artificial intelligence with deep decision tree classification

Natarajan Yuvaraj; Victor Chang; Balasubramanian Gobinathan; Arulprakash Pinagapani; Srihari Kannan; Gaurav Dhiman; Arsath Raja Rajan

doi:10.1016/j.compeleceng.2021.107186

Automatic detection of cyberbullying using multi-feature based artificial intelligence with deep decision tree classification

Natarajan Yuvaraj
, Victor Chang^*
, Balasubramanian Gobinathan
, Arulprakash Pinagapani
, Srihari Kannan
, Gaurav Dhiman
, Arsath Raja Rajan

^*Corresponding author for this work

ICT Academy
Jaya Sakthi Engineering College
Rathinam Technical Campus
SNS College of Engineering
Government Bikram College of Commerce

Research output: Contribution to journal › Article › peer-review

106 Citations (SciVal)

175 Downloads (Pure)

Abstract

Recent studies have shown that cyberbullying is a rising youth epidemic. In this paper, we develop a novel automated classification model that identifies the cyberbullying texts without fitting them into large dimensional space. On the other hand, a classifier.cannot provide a limited convergent solution due to its overfitting problem. Considering such limitations, we developed a text classification engine that initially pre-processes the tweets, eliminates noise and other background information, extracts the selected features and classifies without data overfitting. The study develops a novel Deep Decision Tree classifier that utilizes the hidden layers of Deep Neural Network (DNN) as its tree node to process the input elements. The validation confirms the accuracy of classification using the novel Deep classifier with its improved text classification accuracy.

Original language	English
Article number	107186
Journal	Computers and Electrical Engineering
Volume	92
Early online date	7 May 2021
DOIs	https://doi.org/10.1016/j.compeleceng.2021.107186
Publication status	Published - 1 Jun 2021

Bibliographical note

© 2021, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/

Funding Information:
This work is partly supported by VC Research (VCR 0000061) for Prof Chang.

Funding

This work is partly supported by VC Research (VCR 0000061) for Prof Chang.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Artificial intelligence
Cyberbullying detection
Decision trees
Deep neural network
Smart city

Access to Document

10.1016/j.compeleceng.2021.107186

Automatic detection of cyberbullying using multi-feature based artificial intelligence
© 2021, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
Accepted author manuscript, 1.01 MBLicence: CC BY-NC-ND 4.0

Cite this

@article{e8b5789147ab4cb3bd53939cf48c2c89,

title = "Automatic detection of cyberbullying using multi-feature based artificial intelligence with deep decision tree classification",

abstract = "Recent studies have shown that cyberbullying is a rising youth epidemic. In this paper, we develop a novel automated classification model that identifies the cyberbullying texts without fitting them into large dimensional space. On the other hand, a classifier.cannot provide a limited convergent solution due to its overfitting problem. Considering such limitations, we developed a text classification engine that initially pre-processes the tweets, eliminates noise and other background information, extracts the selected features and classifies without data overfitting. The study develops a novel Deep Decision Tree classifier that utilizes the hidden layers of Deep Neural Network (DNN) as its tree node to process the input elements. The validation confirms the accuracy of classification using the novel Deep classifier with its improved text classification accuracy.",

keywords = "Artificial intelligence, Cyberbullying detection, Decision trees, Deep neural network, Smart city",

author = "Natarajan Yuvaraj and Victor Chang and Balasubramanian Gobinathan and Arulprakash Pinagapani and Srihari Kannan and Gaurav Dhiman and Rajan, \{Arsath Raja\}",

note = "{\textcopyright} 2021, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ Funding Information: This work is partly supported by VC Research (VCR 0000061) for Prof Chang. ",

year = "2021",

month = jun,

day = "1",

doi = "10.1016/j.compeleceng.2021.107186",

language = "English",

volume = "92",

journal = "Computers and Electrical Engineering",

issn = "0045-7906",

publisher = "Elsevier",

}

TY - JOUR

T1 - Automatic detection of cyberbullying using multi-feature based artificial intelligence with deep decision tree classification

AU - Yuvaraj, Natarajan

AU - Chang, Victor

AU - Gobinathan, Balasubramanian

AU - Pinagapani, Arulprakash

AU - Kannan, Srihari

AU - Dhiman, Gaurav

AU - Rajan, Arsath Raja

N1 - © 2021, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ Funding Information: This work is partly supported by VC Research (VCR 0000061) for Prof Chang.

PY - 2021/6/1

Y1 - 2021/6/1

N2 - Recent studies have shown that cyberbullying is a rising youth epidemic. In this paper, we develop a novel automated classification model that identifies the cyberbullying texts without fitting them into large dimensional space. On the other hand, a classifier.cannot provide a limited convergent solution due to its overfitting problem. Considering such limitations, we developed a text classification engine that initially pre-processes the tweets, eliminates noise and other background information, extracts the selected features and classifies without data overfitting. The study develops a novel Deep Decision Tree classifier that utilizes the hidden layers of Deep Neural Network (DNN) as its tree node to process the input elements. The validation confirms the accuracy of classification using the novel Deep classifier with its improved text classification accuracy.

AB - Recent studies have shown that cyberbullying is a rising youth epidemic. In this paper, we develop a novel automated classification model that identifies the cyberbullying texts without fitting them into large dimensional space. On the other hand, a classifier.cannot provide a limited convergent solution due to its overfitting problem. Considering such limitations, we developed a text classification engine that initially pre-processes the tweets, eliminates noise and other background information, extracts the selected features and classifies without data overfitting. The study develops a novel Deep Decision Tree classifier that utilizes the hidden layers of Deep Neural Network (DNN) as its tree node to process the input elements. The validation confirms the accuracy of classification using the novel Deep classifier with its improved text classification accuracy.

KW - Artificial intelligence

KW - Cyberbullying detection

KW - Decision trees

KW - Deep neural network

KW - Smart city

UR - https://www.scopus.com/pages/publications/85105329157

UR - https://www.sciencedirect.com/science/article/pii/S0045790621001877?via%3Dihub

U2 - 10.1016/j.compeleceng.2021.107186

DO - 10.1016/j.compeleceng.2021.107186

M3 - Article

AN - SCOPUS:85105329157

SN - 0045-7906

VL - 92

JO - Computers and Electrical Engineering

JF - Computers and Electrical Engineering

M1 - 107186

ER -

Automatic detection of cyberbullying using multi-feature based artificial intelligence with deep decision tree classification

Abstract

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this