33 Hits in 6.7 sec

Cyber Bullying and Machine Learning: A Survey

Ibtihaj Alanazi, Jim Alves-Foss
2020 Zenodo  
However, there is a requirement for intelligent systems to identify possible risks automatically, given how the Web is overloaded with massive information.  ...  This paper surveys several attempts to use machine learning technology to detect instances of cyber bullying and summarizes their results.  ...  For the feature extraction stage, two categories of features were leveraged: lexical and behavioral features [15] .  ... 
doi:10.5281/zenodo.4249340 fatcat:rty6mejoqbdghbnf5secickfhq

Exploring high-level features for detecting cyberpedophilia

Dasha Bogdanova, Paolo Rosso, Thamar Solorio
2014 Computer Speech and Language  
The SVM classification results show that the NPS data and the pedophiles' conversations can be accurately discriminated with character n-grams, while in the more complicated case of cybersex logs high-level  ...  features significantly outperform the low-level ones and achieve a 97% accuracy.  ...  Her research was partially supported by Google Research Award.  ... 
doi:10.1016/j.csl.2013.04.007 fatcat:mwqen452pvd3raroqb5xqw4kwi

Classification of Online Grooming on Chat Logs Using Two Term Weighting Schemes

Nur Rafeeqkha Sulaiman, Maheyzah Md. Siraj
2019 International Journal of Innovative Computing  
The performance of these techniques were examined via datasets, and the accuracy of their result was measured by Support Vector Machine (SVM).  ...  Cyber groomers are one of cyber predators who prey on children or minors to satisfy their sexual desire.  ...  The algorithms used are TF.IDF.ICS F and Naïve Bayes algorithm, and SVM is used to identify and classify feature vectors.  ... 
doi:10.11113/ijic.v9n2.239 fatcat:ix266w7lx5gkvogxmakkb4aic4

Detecting Offensive Language in Social Media to Protect Adolescent Online Safety

Ying Chen, Yilu Zhou, Sencun Zhu, Heng Xu
2012 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing  
To bridge this gap, we propose the Lexical Syntactic Feature (LSF) architecture to detect offensive content and identify potential offensive users in social media.  ...  We distinguish the contribution of pejoratives/profanities and obscenities in determining offensive content, and introduce hand-authoring syntactic rules in identifying name-calling harassments.  ...  Part of this research was supported by the U.S. National Science Foundation under grant CAREER 0643906 and CNS-1018302.  ... 
doi:10.1109/socialcom-passat.2012.55 dblp:conf/socialcom/ChenZZX12 fatcat:pb4343kzofca7ceidw2lwbroci

A Systematic Survey of Online Data Mining Technology Intended for Law Enforcement

Matthew Edwards, Awais Rashid, Paul Rayson
2015 ACM Computing Surveys  
Such technologies must be well-designed and rigorously grounded, yet no survey of the online data-mining literature exists which examines their techniques, applications and rigour.  ...  As more and more crime takes on a digital aspect, law enforcement bodies must tackle an online environment generating huge volumes of data.  ...  The authors identify from related work that several sentiment features are linked to sexual predation, and construct a feature set based on sentiment markers.  ... 
doi:10.1145/2811403 fatcat:qpvfebejpfgp5bh3cgykaoumze

Effects of Feature Extraction and Classification Methods on Cyberbully Detection

Esra SARAÇ, Selma Ayşe ÖZEL
2016 Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi  
To perform the experiments dataset is used and the effects of preprocessing methods; several classifiers like C4.5, Naïve Bayes, kNN, and SVM; and information gain and chi square feature  ...  In this study we show the effects of feature extraction, feature selection, and classification methods that are used, on the performance of automatic detection of cyberbullying.  ...  Acknowledgment This study was supported by TUBITAK 2211-C Scholarship and Scientific Research Project Unit of Çukurova University under Grant Number: MMF2013D10.  ... 
doi:10.19113/sdufbed.20964 fatcat:6xugyepsxvcupczdg7b74wh7lu

A Multilingual System for Cyberbullying Detection: Arabic Content Detection using Machine Learning

Batoul Haidar, Maroun Chamoun, Ahmed Serhrouchni
2017 Advances in Science, Technology and Engineering Systems  
Previously, researches dealt with the psychological effects of cyberbullying on the victim and the predator.  ...  With the abundance of Internet and electronic devices bullying has moved its place from schools and backyards into cyberspace; to be now known as Cyberbullying.  ...  others for the purpose of prevention and awareness; and identifying predators with their victims.  ... 
doi:10.25046/aj020634 fatcat:7f332jkprnbybct3hjt5aktzba

Online Social Networks and Writing Styles — A Review of the Multidisciplinary Literature

Kah Yee Tai, Jasbir Dhaliwal, Shafiza Mohd Shariff
2020 IEEE Access  
demographics, personality & behavior, and cybersecurity.  ...  In recent years, author identification has become an active research area, where the major differences are caused by paper or online medium, mode of entry and target audience.  ...  Seventy-seven lexical and 157 syntactic features and two different classifiers, i.e., the SVM with SMO and naive Bayes for deceptive review classification, are used.  ... 
doi:10.1109/access.2020.2985916 fatcat:qpejezxkmveyhmpazdz5a3mf7q

The Language of Legal and Illegal Activity on the Darknet

Leshem Choshen, Dan Eldad, Daniel Hershcovich, Elior Sulem, Omri Abend
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
This paper tackles this gap and performs an in-depth investigation of the characteristics of legal and illegal text in the Darknet, comparing it to a clear net website with similar content as a control  ...  The non-indexed parts of the Internet (the Darknet) have become a haven for both legal and illegal anonymous activity.  ...  Acknowledgments This work was supported by the Israel Science Foundation (grant no. 929/17) and by the HUJI Cyber Security Research Center in conjunction with the Israel National Cyber Bureau in the Prime  ... 
doi:10.18653/v1/p19-1419 dblp:conf/acl/ChoshenEHSA19 fatcat:bfcry3cvo5fd7pya4wmtpm45ay

The Language of Legal and Illegal Activity on the Darknet [article]

Leshem Choshen, Dan Eldad, Daniel Hershcovich, Elior Sulem, Omri Abend
2019 arXiv   pre-print
This paper tackles this gap and performs an in-depth investigation of the characteristics of legal and illegal text in the Darknet, comparing it to a clear net website with similar content as a control  ...  The non-indexed parts of the Internet (the Darknet) have become a haven for both legal and illegal anonymous activity.  ...  Conclusion In this paper we identified several distinguishing factors between legal and illegal texts, taking a variety of approaches, predictive (text classification), application-based (named entity  ... 
arXiv:1905.05543v2 fatcat:ysxevbc6rreirlfm5jeigjohi4

A Framework for Detecting Intentions of Criminal Acts in Social Media: A Case Study on Twitter ‡

Ricardo Resende de Mendonça, Daniel Felix de Brito, Ferrucio de Franco Rosa, Júlio Cesar dos Reis, Rodrigo Bonacin
2020 Information  
We propose a framework and construct software prototypes for the selection of social network posts with criminal slang expressions and automatic classification of these posts according to illocutionary  ...  Criminals use online social networks for various activities by including communication, planning, and execution of criminal acts.  ...  With the victim isolated, sexual predators change their approach and use direct texts with sexual content or video communication.  ... 
doi:10.3390/info11030154 fatcat:ls2plqoq2fdzzkf7re55spjofi

Integrated-system to minimizing cyber harassment in kingdom of Saudi Arabia (KSA)

Fahad Abdullah Moafa, Kamsuriah Ahmad, Waleed Mugahed Al-Rahmi, Noraffandy Yahaya, Yusri Bin Kamin, Mahdi Alamri
2018 International Journal of Engineering & Technology  
The system provides the judge with laws used in issuing the judgment in KSA and UK courts.  ...  The proposed system framework consists two main databases: Lexicon dictionary and Summarized previous cases, by depending on Senti-ment analysis and N-Gram algorithms to match the terms and documents.  ...  Acknowledgements We would like to thank Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia by giving the authors an opportunity to conduct this research.  ... 
doi:10.14419/ijet.v7i4.15149 fatcat:k2szvohoojbmxeuvkflvbqqk54

Profiling School Shooters: Automatic Text-Based Analysis

Yair Neuman, Dan Assaf, Yochai Cohen, James L. Knoll
2015 Frontiers in Psychiatry  
Using a ranking/prioritization procedure, similar to the one used for the automatic identification of sexual predators, we provide support for the validity and relevance of the proposed methodology.  ...  Comparing texts written by 6 school shooters to 6056 texts written by a comparison group of male subjects, we found that the shooters' texts scored significantly higher on the Narcissistic Personality  ...  The Ranking and Prioritization Procedure We followed the logic of the automatic identification of sexual predators (21) .  ... 
doi:10.3389/fpsyt.2015.00086 pmid:26089804 pmcid:PMC4453266 fatcat:nthue6wmfbcbxmagr3j4z2ltvy

Characterizing Pedophile Conversations on the Internet using Online Grooming [article]

Aditi Gupta, Ponnurangam Kumaraguru, Ashish Sureka
2012 arXiv   pre-print
We manually annotated 75 pedophile chat conversations with six stages of online grooming and test several hypothesis on it.  ...  The results of our experiments reveal that relationship forming is the most dominant online grooming stage in contrast to the sexual stage.  ...  Smita Sahay for her inputs on annotation and linking us to the psychology literature. The authors thank all members of PreCog research group at IIIT-Delhi for their support.  ... 
arXiv:1208.4324v1 fatcat:r6bklcuilvd5bmfggiwy4empn4

An Unsupervised Domain-Independent Framework for Automated Detection of Persuasion Tactics in Text [article]

Rahul Radhakrishnan Iyer, Katia Sycara
2019 arXiv   pre-print
Existing works on detecting persuasion in text make use of lexical features for detecting persuasive tactics, without taking advantage of the possible structures inherent in the tactics used.  ...  With the increasing growth of social media, people have started relying heavily on the information shared therein to form opinions and make decisions.  ...  We see that the baseline SVM, on lexical features had considerably high precision but it fell short on recall.  ... 
arXiv:1912.06745v1 fatcat:ig2l6gky25eojgomdlxdm77lei
« Previous Showing results 1 — 15 out of 33 results