Detecting predatory conversations in social media by deep Convolutional Neural Networks

被引:45
作者
Ebrahimi, Mohammadreza [1 ]
Suen, Ching Y. [2 ]
Ormandjieva, Olga [2 ]
机构
[1] Concordia Univ, Ctr Pattern Recognit & Machine Intelligence, EV 11-155,1455 Maisonneuve West, Montreal, PQ H3G 1M8, Canada
[2] Concordia Univ, Dept Comp Sci & Software Engn, Montreal, PQ, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Online predator identification; Convolutional neural network; Predatory conversation; Support vector machine; Deep learning; Word embedding; Language model;
D O I
10.1016/j.diin.2016.07.001
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Automatic identification of predatory conversations in chat logs helps the law enforcement agencies act proactively through early detection of predatory acts in cyberspace. In this paper, we describe the novel application of a deep learning method to the automatic identification of predatory chat conversations in large volumes of chat logs. We present a classifier based on Convolutional Neural Network (CNN) to address this problem domain. The proposed CNN architecture outperforms other classification techniques that are common in this domain including Support Vector Machine (SVM) and regular Neural Network (NN) in terms of classification performance, which is measured by F-1-score. In addition, our experiments show that using existing pre-trained word vectors are not suitable for this specific domain. Furthermore, since the learning algorithm runs in a massively parallel environment (i.e., general-purpose GPU), the approach can benefit a large number of computation units (neurons) compared to when CPU is used. To the best of our knowledge, this is the first time that CNNs are adapted and applied to this application domain. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:33 / 48
页数:16
相关论文
共 50 条
[1]   Universality of deep convolutional neural networks [J].
Zhou, Ding-Xuan .
APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2020, 48 (02) :787-794
[2]   Fusion of Deep Convolutional Neural Networks [J].
Suchy, Robert ;
Ezekiel, Soundararajan ;
Cornacchia, Maria .
2017 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR), 2017,
[3]   Deep Learning for Detecting Building Defects Using Convolutional Neural Networks [J].
Perez, Husein ;
Tah, Joseph H. M. ;
Mosavi, Amir .
SENSORS, 2019, 19 (16)
[4]   Ensembles of Deep Convolutional Neural Networks for Detecting Melanoma in Dermoscopy Images [J].
Tziomaka, Melina ;
Maglogiannis, Ilias .
COMPUTATIONAL COLLECTIVE INTELLIGENCE (ICCCI 2021), 2021, 12876 :523-535
[5]   Social media opinion summarization using emotion cognition and convolutional neural networks [J].
Wu, Peng ;
Li, Xiaotong ;
Shen, Si ;
He, Daqing .
INTERNATIONAL JOURNAL OF INFORMATION MANAGEMENT, 2020, 51
[6]   Mobile Social Media Networks Caching with Convolutional Neural Network [J].
Tsai, Kuo Chun ;
Wang, Li ;
Han, Zhu .
2018 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE WORKSHOPS (WCNCW), 2018, :83-88
[7]   Plankton Classification with Deep Convolutional Neural Networks [J].
Ouyang Py ;
Hu Hong ;
Shi Zhongzhi .
2016 IEEE INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC), 2016, :132-136
[8]   Demodulation of Faded Wireless Signals using Deep Convolutional Neural Networks [J].
Mohammad, Ahmad Saeed ;
Reddy, Narsi ;
James, Fathima ;
Beard, Cory .
2018 IEEE 8TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2018, :969-975
[9]   A Review of Deep Learning Models for Detecting Cyberbullying on Social Media Networks [J].
Batani, John ;
Mbunge, Elliot ;
Muchemwa, Benhildah ;
Gaobotse, Goabaone ;
Gurajena, Caroline ;
Fashoto, Stephen ;
Kavu, Tatenda ;
Dandajena, Kudakwashe .
CYBERNETICS PERSPECTIVES IN SYSTEMS, VOL 3, 2022, 503 :528-550
[10]   Detecting Pneumonia With TensorFlow and Convolutional Neural Networks [J].
Babic, Dejan ;
Jovovic, Ivan ;
Popovic, Tomo ;
Cakic, Stevan ;
Filipovic, Luka .
2022 IEEE INTERNATIONAL CONFERENCE ON OMNI-LAYER INTELLIGENT SYSTEMS (IEEE COINS 2022), 2022, :96-99